Community Blog & Articles

Community Articles

Measuring benchmark optimization in speech recognition

Up to 3.2x Faster Inference with LFM2.5-DSpark

How Much Memory Does Your Agent Actually Need?

Multi-Vector (Late Interaction) Embedding Models with Sentence Transformers

Same Cluster, 33 Points More Utilization: What Changed Was the Order

State of Open Models: Summer 2026 Observations

Record, train, and deploy from one place with Strands Agents, LeRobot, and Hugging Face Storage Buckets

What We Learned by Reproducing 2,200 papers from ICML

Introducing OlmoEarth embeddings: Custom embedding exports from OlmoEarth Studio for downstream analysis

Thinking of ACE? We Can Do It with Fewer Tokens

Build Low-Latency Multilingual Voice Agents: Open Weights & Full Deployment Control with NVIDIA Magpie TTS

Making Knowledge Distillation Cheap Enough to Run at Scale

Meta is back with Muse Glimmer: local, agentic, multimodal, and open source

Baseten on Hugging Face Inference Providers 🔥

NEW Articles from Team or Enterprise organizations will get promoted to the main section.

Community Blog & Articles

LFM2.5 Q4\_0 Checkpoints from Quantization-Aware Distillation

Bedrock-RL: a deterministic Minecraft framework for training and benchmarking VLM agents

New imatrix dataset

Writing Down the Line Between Luck and Skill

We changed one line and the benchmark score moved 0.21 AUROC

LFM2.5-VL-3B for Better and Faster Vision Capabilities for the Edge

ArmBench-ASR: A Benchmark for Armenian ASR

mLateOn: A New SoTA for Multilingual ColBERT-Style Retrieval, Evaluated on HAKARI-Bench

Sleeper Agents and How to Tame Them

VLM Run Gateway: Run GLM-OCR, DeepSeek-OCR-2, dots.mocr with an OpenAI Compatible API

Uncensor any LLM with abliteration

Code a simple RAG from scratch

KV Caching Explained: Optimizing Transformer Inference Efficiency

Norm-Preserving Biprojected Abliteration

NEO-unify: Building Native Multimodal Unified Models End to End

The Open Agent Leaderboard

ECMWF's AI forecasting model is open source: now let's make it easy to run.

FLUX 3 Model Overview: Multimodal Flow Models for Image, Video, Audio, and Action Prediction

SraVaani: How Vision Helps Hearing

Fine-Tune SraVaani on Your Own Speech Data

Measuring benchmark optimization in speech recognition

Up to 3.2x Faster Inference with LFM2.5-DSpark

How Much Memory Does Your Agent Actually Need?

Multi-Vector (Late Interaction) Embedding Models with Sentence Transformers

Same Cluster, 33 Points More Utilization: What Changed Was the Order

State of Open Models: Summer 2026 Observations

Record, train, and deploy from one place with Strands Agents, LeRobot, and Hugging Face Storage Buckets

What We Learned by Reproducing 2,200 papers from ICML

Introducing OlmoEarth embeddings: Custom embedding exports from OlmoEarth Studio for downstream analysis

Thinking of ACE? We Can Do It with Fewer Tokens

Build Low-Latency Multilingual Voice Agents: Open Weights & Full Deployment Control with NVIDIA Magpie TTS

Making Knowledge Distillation Cheap Enough to Run at Scale

Meta is back with Muse Glimmer: local, agentic, multimodal, and open source

Baseten on Hugging Face Inference Providers 🔥

LFM2.5 Q4\_0 Checkpoints from Quantization-Aware Distillation

Bedrock-RL: a deterministic Minecraft framework for training and benchmarking VLM agents

New imatrix dataset

Writing Down the Line Between Luck and Skill

We changed one line and the benchmark score moved 0.21 AUROC

LFM2.5-VL-3B for Better and Faster Vision Capabilities for the Edge

ArmBench-ASR: A Benchmark for Armenian ASR

mLateOn: A New SoTA for Multilingual ColBERT-Style Retrieval, Evaluated on HAKARI-Bench

Sleeper Agents and How to Tame Them

VLM Run Gateway: Run GLM-OCR, DeepSeek-OCR-2, dots.mocr with an OpenAI Compatible API

Uncensor any LLM with abliteration

Code a simple RAG from scratch

KV Caching Explained: Optimizing Transformer Inference Efficiency

Norm-Preserving Biprojected Abliteration

NEO-unify: Building Native Multimodal Unified Models End to End

The Open Agent Leaderboard

ECMWF's AI forecasting model is open source: now let's make it easy to run.

FLUX 3 Model Overview: Multimodal Flow Models for Image, Video, Audio, and Action Prediction

SraVaani: How Vision Helps Hearing

Fine-Tune SraVaani on Your Own Speech Data