# Ollama

Ollama

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## Making open models work for long-horizon agentic workloads

DevFeed: [Making open models work for long-horizon agentic workloads](<https://devfeed.tech/articles/making-open-models-work-for-long-horizon-agentic-workloads-141159.md>)

Original publisher: [Read original article](<https://ollama.com/blog/open-models-long-horizon-agents>)

Published: 2026-11-16T00:00:00Z

Content type: article

Language: en

Sources: [Ollama](<https://devfeed.tech/sources/ollama.md>)

Topics: [LLM optimization](<https://devfeed.tech/topics/llm-optimization.md>), [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>), [AI Infrastructure](<https://devfeed.tech/topics/ai-infrastructure.md>), [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [coding assistant](<https://devfeed.tech/topics/coding-assistant.md>), [Ollama](<https://devfeed.tech/topics/ollama.md>), [Open Source Models & Datasets](<https://devfeed.tech/topics/open-source-models-datasets.md>), [supervisor agent pattern](<https://devfeed.tech/topics/supervisor-agent-pattern.md>)

Tags: [agentic-workloads](<https://devfeed.tech/tags/agentic-workloads.md>), [agents](<https://devfeed.tech/tags/agents.md>), [api](<https://devfeed.tech/tags/api.md>), [cache](<https://devfeed.tech/tags/cache.md>), [coding](<https://devfeed.tech/tags/coding.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [conversations](<https://devfeed.tech/tags/conversations.md>), [inference](<https://devfeed.tech/tags/inference.md>), [model](<https://devfeed.tech/tags/model.md>), [models](<https://devfeed.tech/tags/models.md>), [prefix-caching](<https://devfeed.tech/tags/prefix-caching.md>), [prompts](<https://devfeed.tech/tags/prompts.md>), [routing](<https://devfeed.tech/tags/routing.md>)

### AI overview

Long coding-agent sessions repeatedly resend the full conversation while producing short tool calls, so preserving prefix-cache hits can reduce repeated prompt processing. The harness should keep early prompt content stable, place changing session details in the task message, choose reasoning effort at the start, disclose when tool output is truncated, and avoid giving subagents irrelevant history. Loading tools at the end can preserve the cached prefix, but some model templates do not support it. The inference engine must route turns to a node holding the cache and keep idle caches available; routing may choose a cache miss if the warm node is overloaded. The article describes offloading idle caches to CPU memory, paged cache allocation, continuous batching, and separate prefill and decode clusters. Caching reduces recomputation but is not free: cached tokens still consume memory and attention work.

### Source excerpt

Prefix caching helps coding agents stay fast as conversations grow. Prompts, tool calls, and inference routing determine how much work the model can reuse.

## Speech models in Ollama

DevFeed: [Speech models in Ollama](<https://devfeed.tech/articles/speech-models-in-ollama-99190.md>)

Original publisher: [Read original article](<https://ollama.com/blog/speech-models>)

Published: 2026-10-24T00:00:00Z

Content type: release

Language: en

Sources: [Ollama](<https://devfeed.tech/sources/ollama.md>)

Topics: [Ollama](<https://devfeed.tech/topics/ollama.md>), [Speech Processing](<https://devfeed.tech/topics/speech-processing.md>), [MLX](<https://devfeed.tech/topics/mlx.md>)

Tags: [api](<https://devfeed.tech/tags/api.md>), [apple-silicon](<https://devfeed.tech/tags/apple-silicon.md>), [gradium](<https://devfeed.tech/tags/gradium.md>), [ollama](<https://devfeed.tech/tags/ollama.md>), [phonon](<https://devfeed.tech/tags/phonon.md>), [speech](<https://devfeed.tech/tags/speech.md>), [speech-models](<https://devfeed.tech/tags/speech-models.md>), [text](<https://devfeed.tech/tags/text.md>), [voices](<https://devfeed.tech/tags/voices.md>)

### AI overview

Ollama's first speech model is Phonon from Gradium, available on macOS with Apple Silicon acceleration; Windows and Linux support is described as coming soon. On an M5 Max MacBook Pro, Ollama reports 35% faster performance than Gradium's runtime and accuracy matching the Hugging Face Transformers reference by word error rate. Text-to-speech can stream from the command line or the OpenAI-compatible `/v1/audio/speech` endpoint, and chat replies can be piped to Phonon so playback begins after the first sentence. The excerpt describes five languages and dozens of voices in its source summary; the article says voices are listed by `ollama show phonon`. Phonon is Apache 2.0, while its 40M models are CC BY-NC 4.0 and limited to noncommercial use. Audio is 24 kHz mono, WAV by default or raw 16-bit samples with `response_format: pcm`.

### Source excerpt

Ollama now supports speech models, starting with Phonon from Gradium. Read text aloud in five languages and dozens of voices, streamed as it is generated, over 100 times faster than real time on Apple Silicon.

## Clef is available on Ollama's cloud

DevFeed: [Clef is available on Ollama's cloud](<https://devfeed.tech/articles/clef-is-available-on-ollama-s-cloud-90593.md>)

Original publisher: [Read original article](<https://ollama.com/blog/clef>)

Published: 2026-10-19T00:00:00Z

Content type: release

Language: en

Sources: [Ollama](<https://devfeed.tech/sources/ollama.md>)

Topics: [Ollama](<https://devfeed.tech/topics/ollama.md>), [Local AI](<https://devfeed.tech/topics/local-ai.md>)

Tags: [apache-2-0](<https://devfeed.tech/tags/apache-2-0.md>), [cloudflare](<https://devfeed.tech/tags/cloudflare.md>), [multimodal](<https://devfeed.tech/tags/multimodal.md>)

### AI overview

Cloudflare's Clef, a 27B multimodal decision model fine-tuned from Qwen3.8-27B, is available locally and on Ollama's cloud under Apache 2.0. It converts text and image inputs into typed decisions, supporting request routing, policy checks, document field evaluation, and agent tool-call moderation.

### Source excerpt

Clef, a 27B multimodal decision model from Cloudflare, is now available on Ollama. Run it locally or on Ollama's cloud.

## Reflection's Beam is freely available on Ollama for a limited time

DevFeed: [Reflection's Beam is freely available on Ollama for a limited time](<https://devfeed.tech/articles/reflection-s-beam-is-freely-available-on-ollama-for-a-limited-time-88804.md>)

Original publisher: [Read original article](<https://ollama.com/blog/reflection-beam>)

Published: 2026-10-16T00:00:00Z

Content type: release

Language: en

Sources: [Ollama](<https://devfeed.tech/sources/ollama.md>)

Topics: [Ollama](<https://devfeed.tech/topics/ollama.md>), [gpt-oss](<https://devfeed.tech/topics/gpt-oss.md>), [Loop Engineering](<https://devfeed.tech/topics/loop-engineering.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [agents](<https://devfeed.tech/tags/agents.md>), [apache-2-0](<https://devfeed.tech/tags/apache-2-0.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [model](<https://devfeed.tech/tags/model.md>), [ollama](<https://devfeed.tech/tags/ollama.md>)

### AI overview

Reflection's first open-weight model, Beam, is available through Ollama Cloud for free for a limited time. It is designed for software engineering, reasoning, and long-running agentic workflows, and Ollama says its endpoint uses zero data retention.

### Source excerpt

Reflection's first open-weight model is now available on Ollama, and free for a limited time only. Beam is designed for software engineering, reasoning, and long-running agentic tasks. Access Beam through Ollama Cloud.

## Run AI agents safely with Ollama and Fly.io

DevFeed: [Run AI agents safely with Ollama and Fly.io](<https://devfeed.tech/articles/run-ai-agents-safely-with-ollama-and-fly-io-86260.md>)

Original publisher: [Read original article](<https://ollama.com/blog/fly-io-sprites>)

Published: 2026-10-13T00:00:00Z

Content type: release

Language: en

Sources: [Ollama](<https://devfeed.tech/sources/ollama.md>)

Topics: [Ollama](<https://devfeed.tech/topics/ollama.md>), [fly.io](<https://devfeed.tech/topics/fly-io.md>), [virtual machines](<https://devfeed.tech/topics/virtual-machines.md>), [AI Infrastructure](<https://devfeed.tech/topics/ai-infrastructure.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [authorization](<https://devfeed.tech/tags/authorization.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [curl](<https://devfeed.tech/tags/curl.md>), [fly-io](<https://devfeed.tech/tags/fly-io.md>), [ollama](<https://devfeed.tech/tags/ollama.md>)

### AI overview

Ollama Cloud models can now be used from Fly.io Sprites, persistent Linux virtual machines designed for agents. A Fly.io gateway adds the Ollama API key to requests, keeping it out of the Sprite while access controls determine which Sprites can use the connector. The article also gives setup steps, API examples, and a fuzzing workflow using multiple models.

### Source excerpt

AI agents can now use Ollama's cloud models safely inside Fly.io's cloud computers.

## Ollama now supports Jev-style decision models

DevFeed: [Ollama now supports Jev-style decision models](<https://devfeed.tech/articles/ollama-now-supports-jev-style-decision-models-83399.md>)

Original publisher: [Read original article](<https://ollama.com/blog/ollama-now-supports-jev-style-decision-models>)

Published: 2026-09-29T00:00:00Z

Content type: release

Language: en

Sources: [Ollama](<https://devfeed.tech/sources/ollama.md>)

Topics: [Ollama](<https://devfeed.tech/topics/ollama.md>), [decision-making](<https://devfeed.tech/topics/decision-making.md>), [Claude](<https://devfeed.tech/topics/claude.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [api](<https://devfeed.tech/tags/api.md>), [decision-models](<https://devfeed.tech/tags/decision-models.md>), [jev](<https://devfeed.tech/tags/jev.md>), [latency](<https://devfeed.tech/tags/latency.md>), [low-latency](<https://devfeed.tech/tags/low-latency.md>)

### AI overview

Ollama 0.35 adds a `/v1/systemone` endpoint for running Jev-style decision models locally. The release describes three available models and a single-request API that returns answers to named questions, with examples including ticket triage, model routing, and content moderation.

### Source excerpt

Ollama now supports decision models, based on TypeSafe's Jev API for fast, typed decisions. Decision models can now be run at no cost with low latency. Based on text, decision models answer yes-or-no questions, choices and scores about it, with a probability for every option.

## Ollama's transparent pricing

DevFeed: [Ollama's transparent pricing](<https://devfeed.tech/articles/ollama-s-transparent-pricing-83414.md>)

Original publisher: [Read original article](<https://ollama.com/blog/transparent-pricing>)

Published: 2026-08-31T00:00:00Z

Content type: release

Language: en

Sources: [Ollama](<https://devfeed.tech/sources/ollama.md>)

Topics: [Ollama](<https://devfeed.tech/topics/ollama.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>)

Tags: [codex](<https://devfeed.tech/tags/codex.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [ollama](<https://devfeed.tech/tags/ollama.md>), [pricing](<https://devfeed.tech/tags/pricing.md>), [team](<https://devfeed.tech/tags/team.md>), [token](<https://devfeed.tech/tags/token.md>)

### AI overview

Ollama has introduced transparent per-token pricing for its Pro, Max, and Team plans, each with monthly usage credits. The announcement describes included amounts, pay-as-you-go usage, unlimited seats on the Team plan, and continued access to existing plans for current subscribers.

### Source excerpt

Ollama's Pro, Max, and Team plans now use industry-standard per-token pricing with usage included on every plan.

## Claude Desktop support with Ollama

DevFeed: [Claude Desktop support with Ollama](<https://devfeed.tech/articles/claude-desktop-support-with-ollama-83364.md>)

Original publisher: [Read original article](<https://ollama.com/blog/claude-desktop>)

Published: 2026-08-25T00:00:00Z

Content type: release

Language: en

Sources: [Ollama](<https://devfeed.tech/sources/ollama.md>)

Topics: [Ollama](<https://devfeed.tech/topics/ollama.md>), [Claude](<https://devfeed.tech/topics/claude.md>), [anthropic](<https://devfeed.tech/topics/anthropic.md>)

Tags: [anthropic](<https://devfeed.tech/tags/anthropic.md>), [claude](<https://devfeed.tech/tags/claude.md>), [coding](<https://devfeed.tech/tags/coding.md>), [data-retention](<https://devfeed.tech/tags/data-retention.md>), [developers](<https://devfeed.tech/tags/developers.md>), [local](<https://devfeed.tech/tags/local.md>), [local-model](<https://devfeed.tech/tags/local-model.md>), [local-models](<https://devfeed.tech/tags/local-models.md>), [ollama](<https://devfeed.tech/tags/ollama.md>), [zero-data-retention](<https://devfeed.tech/tags/zero-data-retention.md>)

### AI overview

Ollama now lets developers configure Claude Desktop as a gateway to use Ollama models, including open models running locally or in the cloud. Users can switch back to Anthropic models through Ollama. The article also says telemetry is disabled by default and describes a Zero Data Retention policy for its models and services.

### Source excerpt

Claude Desktop can now be configured to work with Ollama as a third-party gateway provider, making it possible to use open models in Claude.

## NVIDIA Nemotron 3.5 Lightning

DevFeed: [NVIDIA Nemotron 3.5 Lightning](<https://devfeed.tech/articles/nvidia-nemotron-3-5-lightning-83392.md>)

Original publisher: [Read original article](<https://ollama.com/blog/nemotron-3-5-lightning>)

Published: 2026-08-11T00:00:00Z

Content type: release

Language: en

Sources: [Ollama](<https://devfeed.tech/sources/ollama.md>)

Topics: [Nemotron](<https://devfeed.tech/topics/nemotron.md>), [Local AI](<https://devfeed.tech/topics/local-ai.md>), [Agent Harness](<https://devfeed.tech/topics/agent-harness.md>), [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agent-harnesses](<https://devfeed.tech/tags/agent-harnesses.md>), [agentic-coding](<https://devfeed.tech/tags/agentic-coding.md>), [agents](<https://devfeed.tech/tags/agents.md>), [apple-silicon](<https://devfeed.tech/tags/apple-silicon.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [cli](<https://devfeed.tech/tags/cli.md>), [code](<https://devfeed.tech/tags/code.md>), [context](<https://devfeed.tech/tags/context.md>), [dgx-spark](<https://devfeed.tech/tags/dgx-spark.md>), [dgx-station](<https://devfeed.tech/tags/dgx-station.md>), [inference](<https://devfeed.tech/tags/inference.md>), [nemotron](<https://devfeed.tech/tags/nemotron.md>), [nemotron-3-5-lightning](<https://devfeed.tech/tags/nemotron-3-5-lightning.md>), [nvidia-nemotron](<https://devfeed.tech/tags/nvidia-nemotron.md>), [ollama](<https://devfeed.tech/tags/ollama.md>), [tasks](<https://devfeed.tech/tags/tasks.md>), [tools](<https://devfeed.tech/tags/tools.md>)

### AI overview

NVIDIA Nemotron 3.5 Lightning is available on Ollama as a 30-billion-parameter open model with 3 billion active parameters, designed for long-running agents and multi-step tasks. It runs on local hardware, supports coding sub-agents and tool calling, and offers up to a 1-million-token context window. The article describes inference optimizations and integrations with agent tools.

### Source excerpt

NVIDIA Nemotron 3.5 Lightning is now available on Ollama. It's a 30 billion parameter (3B active) open model built for agents that stay running, gathering context, calling tools, and working through multi-step tasks on your own hardware.

## Muse Glimmer from Meta Superintelligence Labs is now available

DevFeed: [Muse Glimmer from Meta Superintelligence Labs is now available](<https://devfeed.tech/articles/muse-glimmer-from-meta-superintelligence-labs-is-now-available-83391.md>)

Original publisher: [Read original article](<https://ollama.com/blog/muse-glimmer>)

Published: 2026-08-10T00:00:00Z

Content type: release

Language: en

Sources: [Ollama](<https://devfeed.tech/sources/ollama.md>)

Topics: [Ollama](<https://devfeed.tech/topics/ollama.md>), [GitHub Copilot](<https://devfeed.tech/topics/github-copilot.md>), [Local AI](<https://devfeed.tech/topics/local-ai.md>), [MLX](<https://devfeed.tech/topics/mlx.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [apache-2-0](<https://devfeed.tech/tags/apache-2-0.md>), [apple](<https://devfeed.tech/tags/apple.md>), [apple-silicon](<https://devfeed.tech/tags/apple-silicon.md>), [coding](<https://devfeed.tech/tags/coding.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [computer-use](<https://devfeed.tech/tags/computer-use.md>), [dflash](<https://devfeed.tech/tags/dflash.md>), [meta-superintelligence-labs](<https://devfeed.tech/tags/meta-superintelligence-labs.md>), [mlx](<https://devfeed.tech/tags/mlx.md>)

### AI overview

Meta's Muse Glimmer, a 30B open multimodal model, is available through Ollama for local coding agents and personal assistants. The release describes running it with several agent tools and reports 1.5x-1.8x faster performance on Apple Silicon with Ollama's MLX engine and DFlash support. It also adds image input for tasks such as working from mockups, screenshots, and documents.

### Source excerpt

Meta's Muse Glimmer, the first open model released by Meta Superintelligence Labs, is now available. Muse Glimmer is a 30B multimodal model released under the Apache 2.0 license, designed for local coding agents, and accelerated by Ollama's MLX engine with new native DFlash and image input support.

## Ollama: all aboard open models

DevFeed: [Ollama: all aboard open models](<https://devfeed.tech/articles/ollama-all-aboard-open-models-83360.md>)

Original publisher: [Read original article](<https://ollama.com/blog/all-aboard-open-models>)

Published: 2026-07-09T00:00:00Z

Content type: news

Language: en

Sources: [Ollama](<https://devfeed.tech/sources/ollama.md>)

Topics: [Ollama](<https://devfeed.tech/topics/ollama.md>), [Open Source Models & Datasets](<https://devfeed.tech/topics/open-source-models-datasets.md>), [API Business Models](<https://devfeed.tech/topics/api-business-models.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [ai](<https://devfeed.tech/tags/ai.md>), [build](<https://devfeed.tech/tags/build.md>), [models](<https://devfeed.tech/tags/models.md>), [ollama](<https://devfeed.tech/tags/ollama.md>)

### AI overview

Ollama describes its local and cloud platform for running open models, emphasizing developer access, ownership, affordability, and privacy. The company also announces an $88 million funding round and plans for hybrid inference, new model support, and cloud access.

### Source excerpt

Serving 8.9 million developers, Ollama has raised $88M from Benchmark, Theory Ventures, 8VC, Y Combinator, and many incredible angel investors.

## Faster Gemma 4 on MLX with multi-token prediction

DevFeed: [Faster Gemma 4 on MLX with multi-token prediction](<https://devfeed.tech/articles/faster-gemma-4-on-mlx-with-multi-token-prediction-83370.md>)

Original publisher: [Read original article](<https://ollama.com/blog/faster-gemma-4-mlx-mtp>)

Published: 2026-06-29T00:00:00Z

Content type: release

Language: en

Sources: [Ollama](<https://devfeed.tech/sources/ollama.md>)

Topics: [gemma](<https://devfeed.tech/topics/gemma.md>), [MLX](<https://devfeed.tech/topics/mlx.md>), [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [Ollama](<https://devfeed.tech/topics/ollama.md>), [Language models](<https://devfeed.tech/topics/language-models.md>), [AI Infrastructure](<https://devfeed.tech/topics/ai-infrastructure.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [agents](<https://devfeed.tech/tags/agents.md>), [apple-silicon](<https://devfeed.tech/tags/apple-silicon.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [coding](<https://devfeed.tech/tags/coding.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [gemma](<https://devfeed.tech/tags/gemma.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [hardware](<https://devfeed.tech/tags/hardware.md>), [m5-max](<https://devfeed.tech/tags/m5-max.md>), [macos](<https://devfeed.tech/tags/macos.md>), [mlx](<https://devfeed.tech/tags/mlx.md>), [model](<https://devfeed.tech/tags/model.md>), [models](<https://devfeed.tech/tags/models.md>), [mtp](<https://devfeed.tech/tags/mtp.md>), [ollama](<https://devfeed.tech/tags/ollama.md>), [performance](<https://devfeed.tech/tags/performance.md>), [silicon](<https://devfeed.tech/tags/silicon.md>), [token](<https://devfeed.tech/tags/token.md>)

### AI overview

Ollama 0.31 adds multi-token prediction for Gemma 4 on Apple Silicon, with the article reporting nearly 90% faster token generation on average across a coding-agent benchmark. The feature dynamically adjusts draft length, verifies proposed tokens in batches, and uses an MLX kernel to reduce repeated weight reads. The speedup depends on workload and hardware.

### Source excerpt

Gemma 4 is now significantly faster in Ollama 0.31 on Apple Silicon via multi-token prediction (MTP), powered by MLX. Performance is now up to 90% faster when used with coding agents, as measured using the Aider polyglot benchmark.

## Ollama's highest performance on Apple Silicon yet with MLX

DevFeed: [Ollama's highest performance on Apple Silicon yet with MLX](<https://devfeed.tech/articles/ollama-s-highest-performance-on-apple-silicon-yet-with-mlx-83389.md>)

Original publisher: [Read original article](<https://ollama.com/blog/mlx-performance>)

Published: 2026-06-11T00:00:00Z

Content type: release

Language: en

Sources: [Ollama](<https://devfeed.tech/sources/ollama.md>)

Topics: [MLX](<https://devfeed.tech/topics/mlx.md>), [Ollama](<https://devfeed.tech/topics/ollama.md>), [scaling laws](<https://devfeed.tech/topics/scaling-laws.md>), [GPU optimization](<https://devfeed.tech/topics/gpu-optimization.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>)

Tags: [agent-workflows](<https://devfeed.tech/tags/agent-workflows.md>), [apple-silicon](<https://devfeed.tech/tags/apple-silicon.md>), [coding-agent](<https://devfeed.tech/tags/coding-agent.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [local](<https://devfeed.tech/tags/local.md>), [mlx](<https://devfeed.tech/tags/mlx.md>), [nvfp4](<https://devfeed.tech/tags/nvfp4.md>), [ollama](<https://devfeed.tech/tags/ollama.md>), [performance](<https://devfeed.tech/tags/performance.md>)

### AI overview

Ollama's updated MLX engine for Apple Silicon supports NVIDIA's NVFP4 format, with the release describing higher quality responses, faster output, and lower memory use. It also adds selective model-state snapshots to reduce repeated prompt processing in agent workflows, including handoffs, branching, and retries.

### Source excerpt

Ollama's MLX engine has been updated to deliver its highest performance on Apple Silicon yet. Models output higher quality responses, respond faster, and use less memory.

## Improved performance and model support with GGUF

DevFeed: [Improved performance and model support with GGUF](<https://devfeed.tech/articles/improved-performance-and-model-support-with-gguf-83379.md>)

Original publisher: [Read original article](<https://ollama.com/blog/improved-performance-and-model-support-with-gguf>)

Published: 2026-06-05T00:00:00Z

Content type: release

Language: en

Sources: [Ollama](<https://devfeed.tech/sources/ollama.md>)

Topics: [Ollama](<https://devfeed.tech/topics/ollama.md>), [llama.cpp](<https://devfeed.tech/topics/llama-cpp.md>), [quantization](<https://devfeed.tech/topics/quantization.md>), [tgi](<https://devfeed.tech/topics/tgi.md>)

Tags: [apple-silicon](<https://devfeed.tech/tags/apple-silicon.md>), [coding](<https://devfeed.tech/tags/coding.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [gguf](<https://devfeed.tech/tags/gguf.md>), [hardware](<https://devfeed.tech/tags/hardware.md>), [llama-cpp](<https://devfeed.tech/tags/llama-cpp.md>), [mlx](<https://devfeed.tech/tags/mlx.md>), [model-support](<https://devfeed.tech/tags/model-support.md>), [ollama](<https://devfeed.tech/tags/ollama.md>), [performance](<https://devfeed.tech/tags/performance.md>), [run](<https://devfeed.tech/tags/run.md>)

### AI overview

Ollama 0.30 adds GGUF compatibility through llama.cpp alongside its MLX engine on Apple silicon. The release reports up to 20% faster performance on NVIDIA hardware and enables Vulkan by default to extend GPU acceleration to AMD and Intel devices. It also expands model compatibility and describes how to run GGUF models from Hugging Face, including connecting models with tool calling to coding agents and assistants.

### Source excerpt

Ollama 0.30 is now available with improved performance and GGUF model compatibility through llama.cpp. This augments Ollama's MLX engine on Apple silicon, bringing support to more models on a wider range of hardware.

## NVIDIA Nemotron 3 Ultra

DevFeed: [NVIDIA Nemotron 3 Ultra](<https://devfeed.tech/articles/nvidia-nemotron-3-ultra-83393.md>)

Original publisher: [Read original article](<https://ollama.com/blog/nemotron-3-ultra>)

Published: 2026-06-04T00:00:00Z

Content type: release

Language: en

Sources: [Ollama](<https://devfeed.tech/sources/ollama.md>)

Topics: [Nemotron](<https://devfeed.tech/topics/nemotron.md>), [Ollama](<https://devfeed.tech/topics/ollama.md>), [NVFP4](<https://devfeed.tech/topics/nvfp4.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [costs](<https://devfeed.tech/tags/costs.md>), [efficiency](<https://devfeed.tech/tags/efficiency.md>), [nemotron](<https://devfeed.tech/tags/nemotron.md>), [nvidia](<https://devfeed.tech/tags/nvidia.md>), [ollama](<https://devfeed.tech/tags/ollama.md>), [productivity](<https://devfeed.tech/tags/productivity.md>), [workflows](<https://devfeed.tech/tags/workflows.md>)

### AI overview

NVIDIA Nemotron 3 Ultra is available on Ollama's cloud as a 550-billion-parameter model with 55 billion active parameters. It is designed for long-running agent workflows, coding agents, and deep research, with a one-million-token context window. The release highlights NVFP4 optimization and reports benchmark performance and cost savings against other leading open models.

### Source excerpt

NVIDIA Nemotron 3 Ultra is built for high-throughput reasoning and long-running agent workflows.

## OpenJarvis: a local-first personal AI is now available to run with Ollama

DevFeed: [OpenJarvis: a local-first personal AI is now available to run with Ollama](<https://devfeed.tech/articles/openjarvis-a-local-first-personal-ai-is-now-available-to-run-with-ollama-83403.md>)

Original publisher: [Read original article](<https://ollama.com/blog/openjarvis>)

Published: 2026-05-28T00:00:00Z

Content type: release

Language: en

Sources: [Ollama](<https://devfeed.tech/sources/ollama.md>)

Topics: [Local AI](<https://devfeed.tech/topics/local-ai.md>), [Ollama](<https://devfeed.tech/topics/ollama.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [hardware](<https://devfeed.tech/tags/hardware.md>), [local](<https://devfeed.tech/tags/local.md>), [local-first](<https://devfeed.tech/tags/local-first.md>), [news](<https://devfeed.tech/tags/news.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [openjarvis](<https://devfeed.tech/tags/openjarvis.md>), [v1](<https://devfeed.tech/tags/v1.md>)

### AI overview

OpenJarvis v1.0 is an open-source framework for personal AI agents that run locally, with cloud use optional and built-in Ollama support. The article describes installation, model selection, and presets for briefings, research, and coding.

### Source excerpt

OpenJarvis v1.0 is now available: an open-source framework for building personal AI agents that run on your own hardware, with Ollama support built-in.

## Ollama is now powered by MLX on Apple Silicon in preview

DevFeed: [Ollama is now powered by MLX on Apple Silicon in preview](<https://devfeed.tech/articles/ollama-is-now-powered-by-mlx-on-apple-silicon-in-preview-83388.md>)

Original publisher: [Read original article](<https://ollama.com/blog/mlx>)

Published: 2026-03-30T00:00:00Z

Content type: release

Language: en

Sources: [Ollama](<https://devfeed.tech/sources/ollama.md>)

Topics: [MLX](<https://devfeed.tech/topics/mlx.md>), [Ollama](<https://devfeed.tech/topics/ollama.md>), [AI tools for developers](<https://devfeed.tech/topics/ai-tools-for-developers.md>), [Local AI](<https://devfeed.tech/topics/local-ai.md>), [Language models](<https://devfeed.tech/topics/language-models.md>), [GPU](<https://devfeed.tech/topics/gpu.md>)

Tags: [apple](<https://devfeed.tech/tags/apple.md>), [apple-silicon](<https://devfeed.tech/tags/apple-silicon.md>), [claude](<https://devfeed.tech/tags/claude.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [codex](<https://devfeed.tech/tags/codex.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [cuda](<https://devfeed.tech/tags/cuda.md>), [ggml](<https://devfeed.tech/tags/ggml.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [inference](<https://devfeed.tech/tags/inference.md>), [llama-cpp](<https://devfeed.tech/tags/llama-cpp.md>), [m5-max](<https://devfeed.tech/tags/m5-max.md>), [m5-pro](<https://devfeed.tech/tags/m5-pro.md>), [memory](<https://devfeed.tech/tags/memory.md>), [mlx](<https://devfeed.tech/tags/mlx.md>), [ollama](<https://devfeed.tech/tags/ollama.md>)

### AI overview

Ollama previews a version powered by Apple's MLX framework for Apple silicon, with reported performance gains and updated cache reuse and checkpointing for coding and agentic tasks. It also adds NVFP4 model support and provides commands to try a Qwen3.5 coding model on a Mac with more than 32 GB of unified memory.

### Source excerpt

Today, we're previewing the fastest way to run Ollama on Apple silicon, powered by MLX, Apple's machine learning framework.

## The simplest and fastest way to setup OpenClaw

DevFeed: [The simplest and fastest way to setup OpenClaw](<https://devfeed.tech/articles/the-simplest-and-fastest-way-to-setup-openclaw-83402.md>)

Original publisher: [Read original article](<https://ollama.com/blog/openclaw-tutorial>)

Published: 2026-02-23T00:00:00Z

Content type: tutorial

Language: en

Sources: [Ollama](<https://devfeed.tech/sources/ollama.md>)

Topics: [OpenClaw](<https://devfeed.tech/topics/openclaw.md>), [Ollama](<https://devfeed.tech/topics/ollama.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-assistant](<https://devfeed.tech/tags/ai-assistant.md>), [command](<https://devfeed.tech/tags/command.md>), [linux](<https://devfeed.tech/tags/linux.md>), [local](<https://devfeed.tech/tags/local.md>), [local-models](<https://devfeed.tech/tags/local-models.md>), [node-js](<https://devfeed.tech/tags/node-js.md>), [ollama](<https://devfeed.tech/tags/ollama.md>), [openclaw](<https://devfeed.tech/tags/openclaw.md>), [plugin](<https://devfeed.tech/tags/plugin.md>), [plugins](<https://devfeed.tech/tags/plugins.md>), [risks](<https://devfeed.tech/tags/risks.md>), [setup](<https://devfeed.tech/tags/setup.md>)

### AI overview

This tutorial explains how to install and start OpenClaw with Ollama using a single command, then connect messaging apps and select a model. It also notes security risks because OpenClaw can read files and execute enabled actions.

### Source excerpt

Setup OpenClaw in under two minutes with a single Ollama command.

## Subagents and web search in Claude Code

DevFeed: [Subagents and web search in Claude Code](<https://devfeed.tech/articles/subagents-and-web-search-in-claude-code-83417.md>)

Original publisher: [Read original article](<https://ollama.com/blog/web-search-subagents-claude-code>)

Published: 2026-02-16T00:00:00Z

Content type: release

Language: en

Sources: [Ollama](<https://devfeed.tech/sources/ollama.md>)

Topics: [Claude Code](<https://devfeed.tech/topics/claude-code.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [Google Search](<https://devfeed.tech/topics/google-search.md>), [Ollama](<https://devfeed.tech/topics/ollama.md>)

Tags: [claude-code](<https://devfeed.tech/tags/claude-code.md>), [ollama](<https://devfeed.tech/tags/ollama.md>), [search](<https://devfeed.tech/tags/search.md>), [subagents](<https://devfeed.tech/tags/subagents.md>)

### AI overview

Ollama has added support for subagents and web search in Claude Code. Subagents can handle parallel tasks such as file search, code exploration, and research, while web search is built into the Anthropic compatibility layer and needs no additional configuration.

### Source excerpt

Ollama now supports subagents and web search in Claude Code.

## OpenClaw

DevFeed: [OpenClaw](<https://devfeed.tech/articles/openclaw-83401.md>)

Original publisher: [Read original article](<https://ollama.com/blog/openclaw>)

Published: 2026-02-01T00:00:00Z

Content type: tutorial

Language: en

Sources: [Ollama](<https://devfeed.tech/sources/ollama.md>)

Topics: [OpenClaw](<https://devfeed.tech/topics/openclaw.md>), [Ollama](<https://devfeed.tech/topics/ollama.md>), [Local AI](<https://devfeed.tech/topics/local-ai.md>), [coding assistant](<https://devfeed.tech/topics/coding-assistant.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai-coding-agents](<https://devfeed.tech/tags/ai-coding-agents.md>), [discord](<https://devfeed.tech/tags/discord.md>), [local-ai](<https://devfeed.tech/tags/local-ai.md>), [ollama](<https://devfeed.tech/tags/ollama.md>), [openclaw](<https://devfeed.tech/tags/openclaw.md>), [slack](<https://devfeed.tech/tags/slack.md>), [telegram](<https://devfeed.tech/tags/telegram.md>), [whatsapp](<https://devfeed.tech/tags/whatsapp.md>)

### AI overview

OpenClaw connects messaging platforms to locally running AI coding agents through a centralized gateway. This tutorial covers installation, launching it with Ollama, configuring it, and selecting models with at least 64k tokens of context.

### Source excerpt

OpenClaw is a personal AI assistant that connects your messaging apps to local AI coding agents, all running on your own device.

## ollama launch

DevFeed: [ollama launch](<https://devfeed.tech/articles/ollama-launch-83380.md>)

Original publisher: [Read original article](<https://ollama.com/blog/launch>)

Published: 2026-01-23T00:00:00Z

Content type: tutorial

Language: en

Sources: [Ollama](<https://devfeed.tech/sources/ollama.md>)

Topics: [Ollama](<https://devfeed.tech/topics/ollama.md>), [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [coding assistant](<https://devfeed.tech/topics/coding-assistant.md>), [cursor](<https://devfeed.tech/topics/cursor.md>)

Tags: [codex](<https://devfeed.tech/tags/codex.md>), [coding-tools](<https://devfeed.tech/tags/coding-tools.md>), [local-models](<https://devfeed.tech/tags/local-models.md>), [minimax](<https://devfeed.tech/tags/minimax.md>), [ollama](<https://devfeed.tech/tags/ollama.md>), [opencode](<https://devfeed.tech/tags/opencode.md>), [qwen3](<https://devfeed.tech/tags/qwen3.md>)

### AI overview

Ollama's `launch` command sets up and runs coding tools such as Claude Code, OpenCode, and Codex with local or cloud models. The article shows setup commands, lists supported integrations and recommended models, and describes extended coding sessions through Ollama's cloud service.

### Source excerpt

ollama launch is a new command which sets up and runs coding tools like Claude Code, OpenCode, and Codex with local or cloud models. No environment variables or config files needed.

## Image generation (experimental)

DevFeed: [Image generation (experimental)](<https://devfeed.tech/articles/image-generation-experimental-83378.md>)

Original publisher: [Read original article](<https://ollama.com/blog/image-generation>)

Published: 2026-01-20T00:00:00Z

Content type: tutorial

Language: en

Sources: [Ollama](<https://devfeed.tech/sources/ollama.md>)

Topics: [generative-ai-tools](<https://devfeed.tech/topics/generative-ai-tools.md>), [Ollama](<https://devfeed.tech/topics/ollama.md>), [stable-diffusion](<https://devfeed.tech/topics/stable-diffusion.md>), [ai-image-generator](<https://devfeed.tech/topics/ai-image-generator.md>), [macOS](<https://devfeed.tech/topics/macos.md>), [Windows](<https://devfeed.tech/topics/windows.md>)

Tags: [alibaba](<https://devfeed.tech/tags/alibaba.md>), [apache-2-0](<https://devfeed.tech/tags/apache-2-0.md>), [black-forest-labs](<https://devfeed.tech/tags/black-forest-labs.md>), [image-generation](<https://devfeed.tech/tags/image-generation.md>), [linux](<https://devfeed.tech/tags/linux.md>), [macos](<https://devfeed.tech/tags/macos.md>), [ollama](<https://devfeed.tech/tags/ollama.md>), [windows](<https://devfeed.tech/tags/windows.md>)

### AI overview

Ollama adds experimental image generation on macOS using Z-Image Turbo and FLUX.2 Klein. The article shows how to run the models, where generated images are saved, and how to adjust dimensions, steps, seeds, and negative prompts. Windows and Linux support are listed as upcoming.

### Source excerpt

Generate images locally with Ollama on macOS. Windows and Linux support coming soon.

## Claude Code with Anthropic API compatibility

DevFeed: [Claude Code with Anthropic API compatibility](<https://devfeed.tech/articles/claude-code-with-anthropic-api-compatibility-83363.md>)

Original publisher: [Read original article](<https://ollama.com/blog/claude>)

Published: 2026-01-16T00:00:00Z

Content type: tutorial

Language: en

Sources: [Ollama](<https://devfeed.tech/sources/ollama.md>)

Topics: [Ollama](<https://devfeed.tech/topics/ollama.md>), [Claude Code](<https://devfeed.tech/topics/claude-code.md>), [Claude](<https://devfeed.tech/topics/claude.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-coding](<https://devfeed.tech/tags/agentic-coding.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-sdk](<https://devfeed.tech/tags/ai-sdk.md>), [claude](<https://devfeed.tech/tags/claude.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [models](<https://devfeed.tech/tags/models.md>), [ollama](<https://devfeed.tech/tags/ollama.md>), [tools](<https://devfeed.tech/tags/tools.md>)

### AI overview

Ollama v0.14.0 and later support the Anthropic Messages API, allowing Claude Code to use local or cloud models through Ollama. The guide covers configuration, model recommendations, Anthropic SDK usage in Python and JavaScript, tool calling, and supported features.

### Source excerpt

Ollama is now compatible with the Anthropic Messages API, making it possible to use tools like Claude Code with open models.

## OpenAI Codex with Ollama

DevFeed: [OpenAI Codex with Ollama](<https://devfeed.tech/articles/openai-codex-with-ollama-83366.md>)

Original publisher: [Read original article](<https://ollama.com/blog/codex>)

Published: 2026-01-15T00:00:00Z

Content type: tutorial

Language: en

Sources: [Ollama](<https://devfeed.tech/sources/ollama.md>)

Topics: [codex](<https://devfeed.tech/topics/codex.md>), [Ollama](<https://devfeed.tech/topics/ollama.md>), [gpt-oss](<https://devfeed.tech/topics/gpt-oss.md>)

Tags: [cli](<https://devfeed.tech/tags/cli.md>), [code](<https://devfeed.tech/tags/code.md>), [codex](<https://devfeed.tech/tags/codex.md>), [gpt-oss](<https://devfeed.tech/tags/gpt-oss.md>), [ollama](<https://devfeed.tech/tags/ollama.md>)

### AI overview

The article explains how to use open models through Ollama with OpenAI Codex CLI. It gives the install command, shows how to start Codex in OSS mode, and describes selecting local or cloud models, including a recommendation for at least a 32K-token context window.

### Source excerpt

Open models can be used with OpenAI's Codex CLI through Ollama. Codex can read, modify, and execute code in your working directory using models such as gpt-oss:20b, gpt-oss:120b, or other open-weight alternatives.

[Next page](<https://devfeed.tech/sources/ollama.md?cursor=WyIyMDI2LTAxLTE1VDAwOjAwOjAwKzAwOjAwIiwgIjQ2MzQ4ODRiLWEzZjQtNGY4ZC04ODA4LTg4YTQ2ZTBkNGM4MCJd>)