Boulesis-26B-A4B-9bit
Disclaimer on MLX Patcher — Provided as-is, no warranty of any kind. Read the code before running —...
Disclaimer on MLX Patcher — Provided as-is, no warranty of any kind. Read the code before running —...
MLX 8-bit conversion of OpenBMB/MiniCPM5-2B, a 2B dense Llama-based model for local deployment, coding, reasoning, long-context work, and...
Квантование сообщества графических процессоров Qwen3.8-Flash-Next с таргетингом 2×64 ГБ с таблицей вложений n-грамм/PLE с параметром 51B, обслуживаемой из...
Mirai’s Qwen3.8-27B Large Quantization A large, high-quality quantization of Qwen3.8-27B prepared for efficient local inference on Apple silicon....
> [!NOTE] > This repository contains the NVFP4 version of Granite-4.2-30B. > > Please refer to the original...
An abliterated (refusal-ablated) build of deepseek-ai/DeepSeek-V4-Flash-0731. Produced by a forward-only, closed-form weight edit — no training, no fine-tuning,...
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...
DeepSeek-V4-Flash-0731 with its routed experts reduced from 256 to 132 per layer by router-weighted expert activation pruning (REAP),...
Модель генерации текста Модальности:Генерация текста Задача: Генерация текста Автор: AlphaOxO Теги: mlx, gptx2, custom_code, en, 8-bitЛайков: 3 | ...
NVFP4 маршрутизируемое экспертное квантование deepseek-ai/DeepSeek-V4-Flash-0731, полученное с помощью собственного опубликованного потока NVIDIA Model-Optimizerdeepseekv4 `(modelopt 0.45.0). На момент публикации...