Qwen-3.6-unsloth-mlx Collection AWQ-style pre-scaling using Unsloth's imatrix calibration data, then 3-6-bit affine quantization with the Unsloth mixed-precision recipe via MLX • 18 items • Updated 23 days ago • 19
RikkaBotan/stable-static-embedding-fast-retrieval-mrl-en Sentence Similarity • 15.6M • Updated Mar 16 • 14
view article Article LightOnOCR-2-1B: a lightweight high-performance end-to-end OCR model family lightonai • Jan 19 • 94
view article Article Supercharge your OCR Pipelines with Open Models +5 merve, ariG23498, davanstrien, hynky, andito, reach-vb, pcuenq • Oct 21, 2025 • 314
lmstudio-community/Qwen3-4B-Thinking-2507-MLX-4bit Text Generation • 0.6B • Updated Aug 6, 2025 • 60.8k • 14
view article Article Tricks from OpenAI gpt-oss YOU 🫵 can use with transformers +5 ariG23498, sergiopaniego, reach-vb, pcuenq, ArthurZ, SaylorTwift, cyrilvallez • Sep 11, 2025 • 188
Running on A100 66 NuMarkdown 8b Thinking 👁 66 Reasoning model specialized for OCR/Markdown generation.