# Hugging Face - Blog The Hugging Face blog This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## Measuring and Improving Consistency in Repeated Agent Runs DevFeed: [Measuring and Improving Consistency in Repeated Agent Runs]() Original publisher: [Read original article]() Author: Evelyn Duesterwald; Lilian Ngweta; Vatche Isahagian; Jayaram Radhakrishnan; Vinod Muthusamy; Gaodan Fang; Ashwath Vaithinathan Aravindan; Punleuk Oum; G Thomas; Merve Unuvar; Ayhan Sebin; Michał Ulewi Published: 2026-09-15T16:00:44Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [Benchmark](), [Ground truth / benchmark quality](), [model-deployment]() Tags: [agent](), [benchmarks](), [consistency](), [evaluation](), [gpt](), [inference](), [leaderboard](), [model](), [reports](), [standard](), [technical]() ### AI overview This article presents the Consistency Analyzer, a diagnostic for finding decision points where an agent's behavior may change across repeated runs. It introduces consistency guidelines in ALTK-Evolve and reports that they reduced the consistency gap from 24.4 percentage points to 12.0 points without reducing average accuracy. ### Source excerpt That is embarrassing onstage. In production, it is a reliability problem: a workflow that succeeded once may fail the next time a user makes the same request. For mission-critical work, such as reconciling a financial transaction or checking a contract for an obligation, that can be a showstopper. Most benchmarks hide this variability behind an average. On AppWorld, a ReAct agent using GPT-4.1 succeeded on 77.4% of runs across five repetitions. ## Async GRPO with LoRA across HF Jobs: a bucket, a proxy, and no NCCL DevFeed: [Async GRPO with LoRA across HF Jobs: a bucket, a proxy, and no NCCL]() Original publisher: [Read original article]() Author: Amine Dirhoussi; Quentin Gallouédec; Kashif Rasul; Sergio Paniego Published: 2026-09-10T00:00:00Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [lora](), [grpo](), [jobs](), [vllm](), [NCCL](), [async](), [hugging face]() Tags: [async](), [grpo](), [hub](), [hugging-face](), [jobs](), [llm](), [lora](), [nccl](), [open-source](), [rl](), [storage](), [trl](), [vllm]() ### AI overview This article describes asynchronous GRPO training with a LoRA adapter across separate Hugging Face Jobs. The adapter is synchronized to vLLM replicas through a shared Storage Bucket, while a proxy handles authentication, rollout routing, and adapter-load broadcasts. Five runs reduced the time for 500 steps from 3 hours 27 minutes to 53 minutes. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## Rebuilding AUTOMATIC1111 with Gradio Workflow DevFeed: [Rebuilding AUTOMATIC1111 with Gradio Workflow]() Original publisher: [Read original article]() Author: yuvraj sharma; Abubakar Abid Published: 2026-09-10T00:00:00Z Content type: tutorial Language: en Sources: [Hugging Face - Blog]() Topics: [AI Development](), [Graphs](), [stable-diffusion](), [Inference](), [Large Language Model](), [hugging face](), [vlm]() Tags: [automatic1111](), [comfyui](), [diffusion](), [flux](), [gradio](), [hugging-face](), [image-to-image](), [image-to-video](), [inference](), [inference-providers](), [llm](), [models](), [python](), [space](), [spaces](), [text-to-image](), [vlm](), [workflow](), [workflows]() ### AI overview A walkthrough of Workflow1111, a Gradio graph that recreates AUTOMATIC1111-style media pipelines with connected operator nodes for image generation, editing, prompting, and related tasks. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## IBM releases SOTA Granite Time Series PatchTST-FM-r2 model with commercial-friendly license DevFeed: [IBM releases SOTA Granite Time Series PatchTST-FM-r2 model with commercial-friendly license]() Original publisher: [Read original article]() Author: Roman Vaculin; Wesley M Gifford; Jiri Navratil; Chandra Reddy; Ayhan Sebin Published: 2026-09-09T15:36:24Z Content type: release Language: en Sources: [Hugging Face - Blog]() Topics: [foundation-models](), [Temporal data](), [releases](), [benchmarking](), [Open Source Models & Datasets](), [Inference]() Tags: [apache](), [benchmarking](), [foundation-models](), [ibm](), [inference](), [model-architecture](), [open-source](), [releases](), [time-series](), [zero-shot]() ### AI overview IBM released Granite Time Series PatchTST-FM-r2, a roughly 385M-parameter time-series foundation model for zero-shot forecasting. The article covers its architecture, probabilistic forecasting, missing-value imputation, benchmark results, licensing, and available reproducibility resources. ### Source excerpt Time-series foundation models are changing the way forecasting systems are built. Instead of training and maintaining a separate model for every dataset, users can use a pretrained model and generate forecasts zero-shot. IBM has released Granite Time Series PatchTST-FM-r2, the latest model in the Granite TSFM family (github, blog). ## Safety for Whom? Refusing the Right Subset of a Topic, Not the Whole Topic DevFeed: [Safety for Whom? Refusing the Right Subset of a Topic, Not the Whole Topic]() Original publisher: [Read original article]() Author: Antonio Tiene; Alejo Lopez Avila; Iker García-Ferrero Published: 2026-09-08T14:23:07Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [AI Chat]() Tags: [blog](), [deployment](), [experiments](), [hugging-face](), [llm](), [model](), [policy](), [safety](), [training]() ### AI overview The article examines LLM safety policies that refuse harmful requests within a topic while continuing to answer benign requests in that same topic. ### Source excerpt A Blog post by Multiverse Computing on Hugging Face ## NeoMME: an efficient Multimodal-native and Multilingual Encoder DevFeed: [NeoMME: an efficient Multimodal-native and Multilingual Encoder]() Original publisher: [Read original article]() Author: Tony Wu; Aurélien Lac Published: 2026-09-03T13:13:48Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [vlm](), [Fine-tuning](), [Large Language Model](), [GPU]() Tags: [apache](), [architecture](), [diffusion](), [embeddings](), [fine-tuning](), [gpu](), [hugging-face](), [multimodal](), [quantization](), [retrieval](), [training](), [transformers](), [vector](), [vision](), [vlm]() ### AI overview NeoMME is a family of multilingual multimodal encoders trained from scratch with a masked discrete-diffusion objective. It uses one bidirectional Transformer for text tokens and image patches, and is fine-tuned for visual document retrieval with dense and late-interaction embeddings. ### Source excerpt We introduce NeoMME, a family of 260M and 800M multilingual multimodal encoders. Unlike many generative visual language models, NeoMME does not use a separate pretrained vision tower or a causal language model. A single bidirectional Transformer processes both text tokens and raw image patches, and we train the entire model from scratch with a masked discrete-diffusion objective. We fine-tuned NeoMME for visual document retrieval using ColPali's page-image approach. ## Training a coding model to paint watercolours with TRL and OpenEnv DevFeed: [Training a coding model to paint watercolours with TRL and OpenEnv]() Original publisher: [Read original article]() Author: Sergio Paniego Published: 2026-09-03T00:00:00Z Content type: tutorial Language: en Sources: [Hugging Face - Blog]() Topics: [openenv](), [coding](), [Language models](), [hugging face](), [AI Development](), [jobs](), [dataset]() Tags: [ai-art](), [coding](), [grpo](), [guide](), [hugging-face](), [javascript](), [jobs](), [open-source](), [openenv](), [rl](), [spaces](), [training](), [trl]() ### AI overview A tutorial describing an open reproduction of a reinforcement-learning pipeline that trains a coding model to create watercolor-like paintings by writing JavaScript with p5.brush. It uses TRL and OpenEnv, with datasets, environments, training scripts, models, and other artifacts published on Hugging Face. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## Fine-tuning a 350M Model for Better Structured Outputs in 100 GRPO Steps DevFeed: [Fine-tuning a 350M Model for Better Structured Outputs in 100 GRPO Steps]() Original publisher: [Read original article]() Author: Leonie Monigatti; ben burtenshaw; Sergio Paniego Published: 2026-09-03T00:00:00Z Content type: tutorial Language: en Sources: [Hugging Face - Blog]() Topics: [AI Chat]() Tags: [artificial-intelligence](), [benchmark](), [community](), [evaluation](), [fine-tuning](), [gpu](), [grpo](), [guide](), [json](), [llama-cpp](), [llm](), [model](), [nlp](), [open-source](), [python](), [rl](), [training](), [trl]() ### AI overview A tutorial on fine-tuning a 350M language model with GRPO to improve structured-output and JSON Schema compliance, then evaluating it on the IFStruct benchmark. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## Give Your Coding Agents a Memory You Own DevFeed: [Give Your Coding Agents a Memory You Own]() Original publisher: [Read original article]() Author: David Corvoysier Published: 2026-09-03T00:00:00Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [AI-assisted coding](), [Traces](), [Inference](), [dataset]() Tags: [agents](), [announcement](), [coding](), [datasets](), [embedding](), [guide](), [inference](), [local](), [memory](), [open-source](), [retrieval](), [traces]() ### AI overview funes is a local, durable memory layer for coding agents that indexes prior session traces so agents can retrieve past decisions with provenance. It uses a deterministic pipeline with vector and BM25 search, reranking, recency weighting, and local storage. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## BenchMIRT: What are LLM benchmarks actually measuring? DevFeed: [BenchMIRT: What are LLM benchmarks actually measuring?]() Original publisher: [Read original article]() Author: Kyle Wiggers Published: 2026-09-01T21:39:07Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [LLM evaluation / benchmarking](), [Large Language Model](), [benchmarking](), [Jailbreak]() Tags: [benchmarks](), [jailbreak](), [llm](), [reasoning](), [safety]() ### AI overview BenchMIRT is a multidimensional item-response-theory method for auditing what individual prompts in LLM benchmarks measure. It separates capabilities associated with benchmark performance so aggregate scores do not conceal differences among task groups. ### Source excerpt Today we're introducing BenchMIRT, a new method for auditing LLM benchmarks at the level of individual prompts--the questions and tasks a model is scored on. A benchmark is usually designed to measure a particular ability, such as safety, general reasoning, or instruction following. But the individual tasks inside it may depend on more than that stated goal. Take BBQ, a benchmark designed to test whether models rely on social stereotypes. ## Introducing @huggingface/kernels: 200+ WebGPU Kernels for Local AI DevFeed: [Introducing @huggingface/kernels: 200+ WebGPU Kernels for Local AI]() Original publisher: [Read original article]() Author: Nico Martin; Joshua Published: 2026-09-01T00:00:00Z Content type: release Language: en Sources: [Hugging Face - Blog]() Topics: [webgpu](), [Local AI](), [Machine learning](), [Inference](), [benchmarking](), [GPU](), [Optimization]() Tags: [benchmark](), [gpu](), [hub](), [inference](), [javascript](), [kernels](), [local-ai](), [open-source](), [optimization](), [shaders](), [testing](), [webgpu]() ### AI overview Hugging Face releases @huggingface/kernels, a JavaScript library and collection of 207 versioned WebGPU kernel packages for browser-based local AI. It also introduces Fleet, a browser benchmarking and testing suite that gathers opted-in performance and correctness evidence across hardware. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## The Open ASR Leaderboard Adds Its First Global South Language DevFeed: [The Open ASR Leaderboard Adds Its First Global South Language]() Original publisher: [Read original article]() Author: Eric Bezzam; Shobhit Banga; Manas Dhir; Bhaskar Singh; Manmeet Kaur; Aaditya Pareek; Walecha; Sagar Jain; Hanuman Sidh; Vanshika Chhabra Published: 2026-08-28T00:00:00Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [asr](), [Benchmark](), [Human-AI evaluation]() Tags: [artificial-intelligence](), [asr](), [audio](), [benchmark](), [benchmarks](), [contributors](), [datasets](), [devices](), [evaluation](), [leaderboard](), [metrics](), [open](), [open-source](), [research](), [speech]() ### AI overview The Open ASR Leaderboard introduces Monsoon evaluation sets for Hindi in India, expanding coverage beyond European languages and testing how recognition performance varies across populations and conditions. The sets use public and private splits, speaker-disjoint data, detailed speaker attributes, and variation in geography, age, gender, vocabulary, devices, acoustic environments, speech type, speech rate, and transcript validity. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## Training and Finetuning Multi-Vector Embedding Models with Sentence Transformers DevFeed: [Training and Finetuning Multi-Vector Embedding Models with Sentence Transformers]() Original publisher: [Read original article]() Author: Tom Aarsen Published: 2026-08-26T00:00:00Z Content type: tutorial Language: en Sources: [Hugging Face - Blog]() Topics: [sentence-transformers](), [AI search](), [AI, ML & Data Engineering]() Tags: [community](), [datasets](), [embedding](), [embeddings](), [evaluation](), [guide](), [nlp](), [open-source](), [retrieval](), [sentence-transformers](), [training]() ### AI overview A tutorial on finetuning multi-vector embedding models with Sentence Transformers. It explains late-interaction token-level retrieval, training components, and domain-specific retrieval improvements. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## Granite 4.2 LLMs: How They're Built DevFeed: [Granite 4.2 LLMs: How They're Built]() Original publisher: [Read original article]() Author: Yousaf Shah; Swanand Kadhe; Riddhiman Moulick; Ashish Sunil Agrawal; Santosh Borse Published: 2026-08-25T15:14:14Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [Language models](), [AI Chat](), [AI-assisted coding](), [releases]() Tags: [agentic](), [agents](), [apache](), [chain-of-thought](), [code](), [fine-tuning](), [grouped-query-attention](), [ibm](), [llms](), [models](), [post-training](), [reasoning](), [reinforcement-learning](), [sglang](), [tool](), [training](), [transformer-architecture](), [vllm]() ### AI overview Granite 4.2 is a family of 3B, 8B, and 30B dense decoder-only reasoning language models. The article covers their training pipeline, thinking modes, native tool calling, and agentic reinforcement learning for the 8B and 30B models. ### Source excerpt Authors: Granite Team, IBM TL;DR: Granite 4.2 is our first family of dense, decoder-only reasoning LLMs, released in three sizes: 3B, 8B, and 30B. These models are post-trained from Granite-4.1 base models. Granite-4.1 base models were pre-trained from scratch on roughly 15T tokens with a five-phase strategy that extends the context window to 512K tokens, supervised fine-tuned on chain-of-thought, reasoning, and agentic-trajectory data, then post-trained with a multi-stage reinforcement... ## Quantization-Aware Healing: a compressed, 4-bit model that outperforms its full-precision original DevFeed: [Quantization-Aware Healing: a compressed, 4-bit model that outperforms its full-precision original]() Original publisher: [Read original article]() Author: Antonio Tiene; Iker García-Ferrero; Ali Hashemi; Bakbergen Ryskulov Published: 2026-08-25T11:39:24Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [AI Chat]() Tags: [architecture](), [benchmarks](), [blog](), [compression](), [fine-tuning](), [gpt](), [gpt-oss](), [hugging-face](), [llms](), [model](), [post-training](), [quantization](), [rlhf]() ### AI overview The article presents Quantization-Aware Healing (QAH), a method for recovering structurally compressed and 4-bit-quantized LLMs. It contrasts QAH with quantization-aware training and distillation, arguing that the latter can be limited when no independently trained full-precision version of the compressed architecture exists. ### Source excerpt A Blog post by Multiverse Computing on Hugging Face ## Wire It, Run It, Deploy It: AI Workflows in Gradio DevFeed: [Wire It, Run It, Deploy It: AI Workflows in Gradio]() Original publisher: [Read original article]() Author: yuvraj sharma; Abubakar Abid Published: 2026-08-25T00:00:00Z Content type: tutorial Language: en Sources: [Hugging Face - Blog]() Topics: [AI, ML & Data Engineering](), [AI Chat](), [GPU]() Tags: [ai](), [gpu](), [gradio](), [hugging-face](), [inference-providers](), [llm](), [models](), [python](), [rest-api](), [spaces](), [tutorial](), [workflows]() ### AI overview A tutorial on building and deploying Gradio AI workflows as typed-node graphs, with runnable examples for image editing, generation, text-to-speech, dataset analysis, REST endpoints, and GPU-backed Python nodes. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## Measuring benchmark optimization in speech recognition DevFeed: [Measuring benchmark optimization in speech recognition]() Original publisher: [Read original article]() Author: Theo Lebryk; Eric Bezzam; Alice; David Ayllon; Jakub Piotr Cłapa; Jens Madsen; Panagiotis Tzirakis Published: 2026-08-21T00:00:00Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [asr](), [Benchmark](), [benchmark overfitting machine learning](), [Machine learning](), [datasets](), [Open Source]() Tags: [asr](), [audio](), [benchmark](), [datasets](), [errors](), [measurement](), [model](), [open-source](), [research](), [speech](), [transcription]() ### AI overview The article examines benchmark optimization, or "benchmaxxing," in speech recognition. It presents three tests and evaluates 11 open-source ASR models, finding that some reproduced benchmark transcripts even when the audio contradicted them. The research also uses model ensembles and human annotations to identify and validate likely benchmark errors. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## How Hugging Face Inference Endpoints, Jobs, and Buckets Power Search on Papers with Code DevFeed: [How Hugging Face Inference Endpoints, Jobs, and Buckets Power Search on Papers with Code]() Original publisher: [Read original article]() Author: Niels Rogge Published: 2026-08-21T00:00:00Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [AI search](), [inference-endpoints](), [jobs](), [hugging face](), [Embeddings](), [PostgreSQL](), [Retrieval Augmented Generation (RAG)]() Tags: [database](), [embeddings](), [hugging-face](), [inference](), [inference-endpoints](), [jobs](), [latency](), [rag](), [research](), [search](), [storage]() ### AI overview This article explains how Papers with Code uses hybrid search to find research papers through exact keyword matching and semantic vector search. The production system combines PostgreSQL full-text search, pgvector embeddings, reciprocal rank fusion, and Hugging Face Jobs, Storage Buckets, and Inference Endpoints. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## Up to 3.2x Faster Inference with LFM2.5-DSpark DevFeed: [Up to 3.2x Faster Inference with LFM2.5-DSpark]() Original publisher: [Read original article]() Author: Xx; Leonie Monigatti; Fernando Fernandes Neto; Tarek Dakhran; Nathan Ranchin Published: 2026-08-20T16:52:57Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [Inference](), [Large Language Model](), [Latency](), [Streaming](), [sglang](), [GPU](), [Code]() Tags: [agentic](), [benchmark](), [code](), [gpu](), [inference](), [latency](), [llama](), [llama-cpp](), [llm](), [memory](), [on-device](), [streaming]() ### AI overview The article presents LFM2.5-DSpark, a speculative decoding approach that accelerates LLM inference by using a lightweight draft model and verifier. It reports up to 3.18x GPU throughput improvement and up to 2.87x on-device improvement, along with reduced function-calling latency and support for llama.cpp and SGLang. ### Source excerpt - Faster inference: up to 3.18 throughput improvement on a GPU and up to 2.87x on-device. - Toward on-device agentic inference: cuts function-calling latency by 57% on average for LFM2.5-2.6B - Day-one support for llama.cpp and SGLang: LFM-compatible DSpark integration is open-sourced upstream The decode phase in LLM inference is traditionally memory-bound. Most latency comes from streaming weights from DRAM into SRAM, not from intense computation. ## How Much Memory Does Your Agent Actually Need? DevFeed: [How Much Memory Does Your Agent Actually Need?]() Original publisher: [Read original article]() Author: Vatche Isahagian; Gaodan Fang; Jayaram Radhakrishnan; Punleuk Oum; Ashwath Vaithinathan Aravindan; Evelyn Duesterwald; G Thomas; Vinod Muthusamy; Merve Unuvar; Ayhan Sebin Published: 2026-08-18T18:09:38Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [Benchmark](), [Inference](), [long-context](), [gpt-oss](), [deepseek](), [Mixture of Experts (MoE)]() Tags: [agent](), [agentic](), [caching](), [deepseek](), [evaluation](), [gpt-oss](), [inference](), [memory](), [model](), [models](), [moe](), [performance](), [production](), [tokens]() ### AI overview ALTK-Evolve equips agents with agentic memory by distilling reusable guidelines from past trajectories and injecting them at inference time without weight updates or human annotation. An evaluation across eight models found that the effective amount of memory varies by model: stronger models benefited from full guideline sets, weaker models from compact cores plus task-specific retrieval, and saturated models showed no measurable improvement. For gpt-oss-120b, selective retrieval improved task completion by 16.1 percentage points with only a 5% token increase. ### Source excerpt Equipping an agent with agentic memory sounds simple: distill lessons from its past work, put them back in context, and more experience should mean better performance. It doesn't always work that way. When we scaled the evaluation to eight models -- from a 30B dense model to frontier proprietary systems -- one finding stood out: Agentic memory is not a feature you switch on. It's a dose you calibrate to the model. ## Multi-Vector (Late Interaction) Embedding Models with Sentence Transformers DevFeed: [Multi-Vector (Late Interaction) Embedding Models with Sentence Transformers]() Original publisher: [Read original article]() Author: Tom Aarsen; Antoine Chaffin; Raphael Sourty Published: 2026-08-18T00:00:00Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [sentence-transformers](), [Embeddings](), [Open Source]() Tags: [community](), [embedding](), [embeddings](), [guide](), [multimodal](), [nlp](), [open-source](), [retrieval](), [search](), [sentence-transformers](), [transformers](), [vector]() ### AI overview This article explains multi-vector, or late-interaction, embedding models with Sentence Transformers. It covers token-level representations, MaxSim scoring, retrieval over text and page images, integration with search systems, and index-size tradeoffs. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## Same Cluster, 33 Points More Utilization: What Changed Was the Order DevFeed: [Same Cluster, 33 Points More Utilization: What Changed Was the Order]() Original publisher: [Read original article]() Author: Gabriel Pimenta de Freitas Cardoso; Breno de Almeida Beleza; Francisco de Almeida Rocha Alves; Bruno Duarte Published: 2026-08-17T19:46:21Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [GPU](), [benchmarking](), [Benchmark](), [jobs](), [Inference](), [model-deployment]() Tags: [batch](), [benchmark](), [comparison](), [gpu](), [inference](), [jobs](), [real-time](), [training]() ### AI overview The article describes a constraint-aware GPU allocator and compares it with a FIFO scheduler across seven benchmark scenarios. On identical hardware and workloads, the allocator increased GPU utilization by up to 33 percentage points and priority-weighted output by up to 105%. It explains how training, batch inference, quantization, and real-time inference impose different scheduling constraints, especially under contention. ### Source excerpt We built a constraint-aware GPU allocator and benchmarked it against a FIFO scheduler across seven benchmark scenarios. On identical hardware, running identical workloads, GPU utilization rose by as much as 33 percentage points, and priority-weighted output rose in every one of them, by as much as 105%. Nothing about the hardware changed. What changed was the order in which allocation decisions get made. One note on measurement before the numbers start. ## State of Open Models: Summer 2026 Observations DevFeed: [State of Open Models: Summer 2026 Observations]() Original publisher: [Read original article]() Author: Adina Yakefu; Apolinário from multimodal AI art; Irene Solaiman Published: 2026-08-14T00:00:00Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [Artificial Intelligence](), [Open Source](), [quantization](), [datasets](), [Nvidia](), [spaces](), [Hardware](), [Nemotron](), [qwen](), [Benchmark](), [API]() Tags: [api](), [artificial-intelligence](), [benchmark](), [community](), [datasets](), [hardware](), [hub](), [nemotron](), [nvidia](), [open-source](), [quantization](), [qwen](), [research](), [spaces]() ### AI overview This article examines the summer 2026 state of open models, highlighting rapid growth in public model repositories, datasets, and Spaces; the dominance of a small number of repositories in downloads; the rising scale of Chinese open models; differing model portfolio strategies; and the strong role of AMD, NVIDIA, and community quantization in making large models accessible. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## Record, train, and deploy from one place with Strands Agents, LeRobot, and Hugging Face Storage Buckets DevFeed: [Record, train, and deploy from one place with Strands Agents, LeRobot, and Hugging Face Storage Buckets]() Original publisher: [Read original article]() Author: Sundar Raghavan; Steven Palma; Cagatay Cali; Arron Bailiss; Yin Song Published: 2026-08-13T17:16:04Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [lerobot](), [hugging face](), [cloud-infrastructure](), [dataset](), [SDKs](), [Command-line interface](), [Open Source]() Tags: [agents](), [apache](), [aws](), [cli](), [code](), [data](), [datasets](), [hub](), [hugging-face](), [lerobot](), [models](), [open](), [open-source](), [robots](), [storage](), [strands-agents](), [train](), [xet]() ### AI overview This article describes a continuous robotics data loop using Strands Agents, LeRobot, Hugging Face Hub, and Hugging Face Storage Buckets. It covers recording demonstrations, collecting episodes, training policies on growing datasets, deploying checkpoints, and using mutable Xet-backed storage to reduce repeated data transfers. ### Source excerpt Record, train, and deploy from one place with Strands Agents, LeRobot, and Hugging Face Storage Buckets You have an agent that can already record a demonstration and push it to the Hugging Face Hub. Now you want to run that loop continuously: collect episodes through the day, train a policy on the growing dataset, deploy it, and pull the next batch back to improve it. Run that loop once and every piece works. Run it every day and you start paying for the same byte transfers over and over. [Next page]()