Qwen3.6-27B-Abliterated-Heretic-Uncensored-MLX-6bit
This is an MLX release of an abliterated, uncensored version of Qwen’s Qwen3.6-27B with the source image/video payload...
This is an MLX release of an abliterated, uncensored version of Qwen’s Qwen3.6-27B with the source image/video payload...
This quant uses a custom mixed-precision recipe designed specifically for the Qwen3.6-27B dense architecture to maximize quality within...
A dual-teacher distilled variant of Qwen3.6-35B-A3B that combines reasoning behaviors from both GLM-5.1 (754B MoE, SOTA on agentic/coding)...
This model was converted to GGUF format from lordx64/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled using llama.cpp via the ggml.ai’s GGUF-my-repo space. Refer to...
———— | ———————————————————————————————- | The following layers are not quantized to preserve model quality: Tested on a single...
Четырехстороннее слияние MoE архитектуры Qwen 35B-A3B, объединяющее векторы задач из трех специализированных тонких настроек в базовый якорь через...
Text-only ROCmFPX/ROCmFP4 GGUF builds of nightmedia/Qwen3.6-27B-Architect-Polaris2-Fable-B-F451, with the checkpoint’s embedded one-layer MTP draft model preserved. These are experimental...
0 жестких отказов в 842 внутренних тестовых подсказках, 0 жестких отказов в отдельном 126-подсказке и 23/24 проверки согласованности...
Quantized GGUFs of Achilles1089/fable-coder-35B-A3B — a sovereign, open-weights agentic coding model by Dappit Labs. 35B MoE (≈3B active),...
RTX 5090 Windows native GGUF comparison — updated July 19, 2026 Native llama.cpp conversions of NVIDIA and Unsloth...