New in llama.cpp: Decision Models
ggml-org
• • 81Community Blog & Articles
Community Articles
view all
The Agent Said It Was Done. The Database Disagreed.
41
October 3, 2026 
Open-sourcing AstaBrief, the fast report-generation model in Asta
23
October 2, 2026 
AutoSynthData: Generating Training Data for Enterprise Agents
40
October 2, 2026 
audiospeechleaderboard
Open TTS Leaderboard: Scalable Evaluation for Multilingual Text-to-Speech and Voice Cloning
51
September 30, 2026 
NVIDIA Kumo Tabular Sets a New Accuracy-Efficiency Frontier for Tabular Prediction
80
September 29, 2026 
Getting the Source Right, Not Just the Fact: Source-Aware Verification for MCP Agents
19
September 29, 2026 
Holo4: powering generalist computer-use agents
80
September 28, 2026 
rldatasetshub
Welcome RL Environments to the hub
- +3
17
September 28, 2026 
Accelerating vision-language models with LFM2.5-VL-DSpark
49
September 24, 2026 
evaluationresearchcommunity
How UK AISI and EvalEval Are Making Benchmark Results Reproducible
- +5
27
September 22, 2026 
transformersggufkernels
Transformers now runs llama.cpp quants
97
September 22, 2026 
mlxopen-sourcecommunity
Jun Kim, oMLX creator and maintainer, joins Hugging Face to support the MLX community
- +1
88
September 22, 2026 
tokenizerstokenizationrust
tokenizers v1: encode, decode and scaling, measured
86
September 21, 2026 
Your Agent Aced the Task. Will It Do It Again?
119
September 15, 2026 NEW Articles from Team or Enterprise organizations will get promoted to the main section.
New in llama.cpp: Decision Models
ggml-org
• • 81autotrust/JEV-27B-VL: a decision model that learned to see without a single image of training
autotrust
• • 59autotrust/JEV-27B: fast, calibrated decisions and full reasoning from one open model
autotrust
• • 57Introducing Olmo-core 3: Open, scalable training infrastructure for large MoEs
allenai
• • 24The DGX Spark Handbook
exolabs
• • 24Qwen3.8-27B-pi: Effort-Ordered Reasoning for Agentic Coding
bytkim
• • 14YODAS v3: A 1 Million Hour Dataset for the Next Generation of Open Voice AI Research
espnet
• • 32Open Superconductor Challenge: Help Discover the Next 2D Superconductor — From Your Laptop
FINAL-Bench
• • 12Holo3: Breaking the Computer Use Frontier
Hcompany
• • 56How to Use NVIDIA Warp and MjWarp to Accelerate Robotics Simulation and Learning Workflows
nvidia
• • 54Live Human Feedback in the Training Loop: Aligning Diffusion Models with Real People
Rapidata
• • 9How to Use the Jev AI Model: A Step-by-Step Developer Guide
sora-2
• • 39Bringing Humanoids to LeRobot
nepyope
• • 25Anatomy of a bug-fixing agent
huggingface
• • 7Data-center AI, now on a laptop — POCKET-Darwin-180B
FINAL-Bench
• • 7FLUX 3 Action: a world action model you can fine-tune
black-forest-labs
• • 14The Road to Open Source Hell Is Paved With Good Intentions
qgallouedec
• • 13Uncensor any LLM with abliteration
mlabonne
• • 927Diagnosing a slow Hugging Face Trainer run: data loading or compute?
abhinavsriva
• • 5KV Caching Explained: Optimizing Transformer Inference Efficiency
not-lain
• • 426