NVIDIA-Nemotron-3-Nano-4B-OptiQ-4bit
> Built with mlx-optiq, the MLX-native toolkit to quantize, fine-tune, and serve LLMs locally on Apple Silicon, no...
> Built with mlx-optiq, the MLX-native toolkit to quantize, fine-tune, and serve LLMs locally on Apple Silicon, no...
Tencent Hy3-preview — 102 GB on disk (down from ~557 GB BF16 source) — mixed-bit JANGTQK quantization on...
> Important: This model uses the JANGTQ (JANG TurboQuant) quantization format — an extreme-compression variant of JANG for...
Пользовательское квантование moonshotai/Kimi-K2-Instruct > V2 со смешанной точностью под управлением иматрицы FinnTheAI улучшает V1 (352 ГБ однородного Q4KM)...
> Built with mlx-optiq, the MLX-native toolkit to quantize, fine-tune, and serve LLMs locally on Apple Silicon, no...
Mixed-precision MLX build of MiniMaxAI/MiniMax-M2.7, prepared by baa.ai. Settings for both runs match the Recommended inference settings below....
> Важно: Эта модель использует формат квантования ЯНГА — эквивалент GGUF для MLX на Apple Silicon. В настоящее...
INVALID LANGUAGE PAIR SPECIFIED. EXAMPLE: LANGPAIR=EN|IT USING 2 LETTER ISO OR RFC3066 LIKE ZH-CN. ALMOST ALL LANGUAGES SUPPORTED...
MLX Studio — the only app that natively supports JANG models with reasoning Nemotron-Cascade-2-30B-A3B — JANG_2L (2.3-bit, 8-bit...
A 13 GB download: 12,982,426,694 bytes = 12.98 GB = 12.09 GiB. Weights and codebooks are 12,958,885,485 B...