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...
🇬🇧 This model comes in 2 sizes, one repo each. You are on the oQ8e page. Click the...
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...
This repository contains an enhanced oQ6e quantization of Altworld/Hemmingway-1 for MLX and oMLX on Apple silicon. The conversion...
4-bit MLX quantization of Qwen/Qwen3.8-Flash-Next — the qwen4exp architecture: a 512-expert MoE (top-10 routing, 48 layers, hybrid linear/full...
oQ6e (imatrix-enhanced mixed-precision ~6.5 BPW) quantization of the merged IFM/K2-Horizon-7B-Uno model — a diffusion-augmented LLM based on K2-Horizon-7B....
oQ4e (imatrix-enhanced mixed-precision 4-bit) conversion of IFM/K2-Horizon-MoVA-36B-A4B, a sparse Mixture-of-Experts model with Mixture-of-Values attention (36B total / 4B...
Speed-tuned variant of Laguna-S-2.1-oQ4e, the calibrated 4-bit MLX quantization of poolside/Laguna-S-2.1 (118B total, 8B activated per token). Same...
Mixed-precision quantization for Apple Silicon, text-only mode (vision tower stripped). Recommended text-only version — best quality-to-size ratio. Quantized...
— Quantization: oQ2 (sensitivity-driven mixed precision, groupsize=64) — Format: MLX safetensors — Compatible with:** mlx-lm, mlx-vlm, oMLX on...
This model was quantized using oQ mixed-precision quantization. — Model type: qwen3next — Bits: 3 — Group size:...