Models & Labs
Dharma Field Extractor beats frontier LLMs on document parsing
Hugging Face Bloghigh confidence
Why it matters
- →Specialized small models are closing the quality gap with frontier APIs on specific enterprise tasks.
- →Self-hosting a 2B parameter model offers massive cost savings compared to per-token API pricing.
- →The release provides a practical alternative for high-volume document processing without data privacy risks.
Dharma-AI has released Dharma Field Extractor, a 2-billion-parameter model designed to extract structured JSON from unstructured documents. The model, built on top of their DharmaOCR-LITE v1.1 checkpoint, uses a LoRA adapter trained on 43,384 examples covering English, Portuguese, and other languages. In benchmarks against Claude Opus 5 and GPT-5.6 Luna, it achieved higher field-level F1 scores while costing significantly less to run on self-hosted hardware like an NVIDIA L40S.
Read originalThe story around this
Earlier coverage that leads up to this article, and what followed. Lines connect each piece to the closest one after it, converging here.
How we got here
- 1DharmaOCR Outperforms Newer OCR Models
Hugging Face Blog · July 16, 2026 · Related
- 2Asana Accelerates Engineering with OpenAI Codex
OpenAI · August 18, 2026 · Background
- 3Google's ToolGrad Enhances Tool-Use Dataset Generation
Google Research Blog · September 10, 2026 · Background
- 4Together AI: Fine-tune Jev-like classifier for $17
Together AI Blog · September 23, 2026 · Background
- 5llama.cpp fixes JSON schema enforcement in Ling 3.0
llama.cpp Releases · October 4, 2026 · Background
- 6OpenAI releases 722 math manuscripts from frontier model
The Verge AI · October 6, 2026 · Background
- 7OpenAI releases 722 AI-generated math manuscripts
Wes Roth · October 7, 2026 · Background
- 8VocabX cuts SLM inference cost by 77% via specialized vocab
Hugging Face Blog · October 21, 2026 · Background
What happened next
- 9Open Chinese AI Models Match Frontier Labs in Hacking
WIRED AI · November 6, 2026 · Background
- 10llama.cpp adds Kimi K3.1-Pro support
llama.cpp Releases · November 7, 2026 · Background
More from Hugging Face Blog
© Hugging Face BlogResearchagents
ToyBlocks: Controlled simulation for robot learning research
Hugging Face launched ToyBlocks, a controlled simulation framework designed to isolate and study the specific mechanics of robot learning. By focusing on a simple tabletop environment with blocks, it allows researchers to automatically generate massive datasets of tasks and demonstrations without manual teleoperation. This setup enables precise testing of how high-level reasoning models like Molmo 2 interact with low-level action controllers like ManiFlow. The real value lies in reproducibility; scientists can now systematically vary training data to understand exactly why a robot fails or succeeds, moving beyond the black-box nature of current robotics benchmarks.
Hugging Face Blog
© Hugging Face BlogResearchother
Open ASR Leaderboard adds Egyptian and Nigerian English
The Open ASR Leaderboard is expanding its evaluation scope by adding private test sets for Egyptian and Nigerian English, addressing a significant gap in global representation. This update moves beyond the traditional Inner Circle accents to include Outer and Expanding Circle varieties, providing a more realistic benchmark for speech recognition models. By partnering with Liva AI for data collection, Hugging Face ensures these evaluations reflect natural, high-context user interactions rather than artificial tasks. This shift forces developers to optimize for diversity, making model performance metrics more trustworthy and globally relevant.
Hugging Face Blog
© Hugging Face BlogModels & Labsvideo
NVIDIA Cosmos 3 Open Models for World Simulation
NVIDIA is opening up its Cosmos 3 world model family with four new 16B parameter checkpoints, shifting from closed research to open-weight simulation. The release targets two critical domains: autonomous driving and robotics. For self-driving cars, the models generate synchronized camera video and LiDAR data, solving the alignment problem between visual appearance and 3D geometry. For robotics, Sim-Bimanual predicts environmental changes from robot actions, enabling closed-loop policy training. This moves world modeling from passive video generation to interactive simulation where agents can act and observe consequences.
Hugging Face Blog
More in Models & Labs
Models & Labsother
llama.cpp b12177 adds CUDA 13 and ROCm 10
This release quietly closes the hardware gap for local inference by adding default support for CUDA 13.5 and ROCm 10.0 alongside existing CUDA 12 builds. AMD GPU users finally get first-class parity with NVIDIA, while Snapdragon mobile chips gain dedicated NPU acceleration paths. Apple Silicon KleidiAI is explicitly disabled here, a notable regression for Mac performance that suggests ongoing tuning issues. The inclusion of OpenVINO and SYCL backends further cements llama.cpp as the universal runtime for inference across nearly every major silicon architecture.
llama.cpp Releases
Models & Labsmodels
llama.cpp adds Kimi K3.1-Pro support
Kimi’s new K3.1-Pro model joins the llama.cpp ecosystem, bringing a distinct architectural twist to local inference. By replacing full-attention MLA layers with DSA (Dynamic Sparse Attention) and linear-attention KDA layers, this release tests how well sparse caching handles hybrid attention patterns. The implementation keeps indexer precision high to avoid quality loss during top-k selection, ensuring the model runs accurately on consumer hardware. This expands the library’s reach into newer Chinese open-weight models that rely on complex memory management.
llama.cpp Releases
Models & Labsother
llama.cpp b12182 release with CUDA 13 and ROCm 10
This release quietly cements llama.cpp as the universal inference runtime by adding default builds for CUDA 13.5 and ROCm 10.0 across Linux and Windows. The inclusion of ROCm 10 means AMD GPU users no longer need custom compilation to access modern acceleration, effectively closing the gap with NVIDIA's ecosystem support. While KleidiAI on Apple Silicon is disabled in this build, the broader platform coverage ensures that local inference remains accessible on virtually any hardware configuration without manual setup.
llama.cpp Releases