Spark-X2.6-4B-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...
A mixed-precision MLX build of Ornith-1.5-122B, converted on Apple Silicon (M3 Max, 64 GB) and runnable with stock...
1.76 GB model · Four coherent circuit paths · 2.06× faster decoding Leona-Q 1.0 mini brings quantum-inspired tensor...
Квантование GGUF Qwen/Qwen3.8-Flash-Next, 512-экспертной модели смеси экспертов с 262 144-токенами контекста и ввода изображения. Он составляет в среднем...
> TL;DR: VibeThinker-3B at 1.16 GB (3-bit) or 1.35 GB (3.5-bit), compared with 6.18 GB in BF16. >...
> Built with mlx-optiq, the MLX-native toolkit to quantize, fine-tune, and serve LLMs locally on Apple Silicon, no...
FP4-quantized build of orcarouter/Qwen3.8-27B-Uncensored (BF16), preserving the abliteration edits byte-for-byte — this is a quantization of the uncensored...
The bundled DFlash2 draft is now a pre-quantized static FP8 compressed-tensors checkpoint, not a BF16 checkpoint carrying an...
> Созданный с помощью mlx-optiq, набор инструментов MLX-native для квантования, точной настройки и обслуживания LLM локально на Apple...
GGUF build of Qwen/Qwen3.8-27B, capability-validated by baa.ai for faithful, retrieval-grounded reading — a full 27B reader that runs...