Flint-40B-A2.5B-abliterated-oQ8e-BF16-MLX
🇬🇧 This model comes in 2 sizes, one repo each. You are on the oQ8e page. Click the...
Метка: omlx
DeepSeek-V4.1-Flash-1017-UNCENSORED-oQ4e-mtp
Сборка MLX дилигнай/DeepSeek-V4.1-Flash-1017-UNCENSORED-FP8 (нецензурированная версия deepseek-ai/DeepSeek-V4.1-Flash-1017), упакованная с oMLX oQ4e для Apple Silicon. Головка MTP сохранилась. До сих...
Hemmingway-1-oQ6e-mtp
This repository contains an enhanced oQ6e quantization of Altworld/Hemmingway-1 for MLX and oMLX on Apple silicon. The conversion...
Spark-X2.5-4B-Abliterated-Uncensored-MLX-oQ4e-fp16
oQ4e-quantized MLX build (created by xunlinkx with the omlx pipeline) of Mondk/Spark-X2.5-4B-Abliterated-Uncensored for first-class, all-local serving on Apple...
DeepSeek-V4-Flash-0731-AWQ
AWQ-calibrated mixed-precision quantization of DeepSeek-V4-Flash-0731 (304B MoE, 43 layers, 256 routed experts/layer, Hyper-Connections, HISA attention) for Apple Silicon...
Qwen3.6-27B-oQ4-fp16-mtp
Этот репозиторий содержит настраиваемые, только текстовые конфигурации семейства моделей Qwen3.6, оптимизированные явно для агентного кодирования на уровне локального...
Qwopus3.6-27B-Coder-MTP-8bit.mlx
This is an oMLX OptiQ 8-bit package of Jackrong/Qwopus3.6-27B-Coder, built from source revision f22041be82998a006c9fde642c7900fb42aff94e. This variant preserves the...
Qwen3.6-27B-oQ8-fp16-mtp
This repository contains custom-quantized, text-only configurations of the Qwen3.6 model family, optimized explicitly for local repository-level agentic coding...
Qwen3-Coder-Next-oQ2
— Quantization: oQ2 (sensitivity-driven mixed precision, groupsize=64) — Format: MLX safetensors — Compatible with:** mlx-lm, mlx-vlm, oMLX on...
Qwen3.8-Flash-Next-oQ5e-mtp
A high-quality oQ5e quantization of Qwen3.8-Flash-Next, targeting improved reasoning robustness and generation stability over oQ4e while still fitting...