DeepSeek-V4.1-Flash-1017-streaming-repack-exl3
This repo holds streaming EXL3 packs of deepseek-ai/DeepSeek-V4.1-Flash-1017 at revision 1bae0e1088993b9b82de08f59de5be5a34e42170, for mlx-serve. Each pack is a branch....
This repo holds streaming EXL3 packs of deepseek-ai/DeepSeek-V4.1-Flash-1017 at revision 1bae0e1088993b9b82de08f59de5be5a34e42170, for mlx-serve. Each pack is a branch....
Квантование ExLlamaV3 (EXL3) Nanbeige/Nanbeige4.3-33B (плотный каузальный LM 33B, контекстное окно 262k, нативное рассуждение). — Исправлен «addbostoken»: false в...
A smaller EAQ v1 (EXL3 format) quantization of MiniMaxAI/MiniMax-M3.1-Flash: 3.064 bits per weight on average over the quantized...
EAQ v1 (EXL3 format) quantization of MiniMaxAI/MiniMax-M3.1-Flash, 60 layers, 128 routed experts with top-4 routing, 3.55 bits per...
EXL3 (trellis-coded) weights of Qwen/Qwen3.8-Flash-Next in a GGUF container, for Rulith Inference on AMD Strix Halo (Windows). The...
Same model, different name. Pull from the UNCENSORED repo above — it’s the one that holds the shards,...
Model size: 309B parameters (15B active). The «52B params» figure in the Hugging Face sidebar is not a...
> ❤️ Please leave a LIKE / HEART on this Hugging Face repository! > If you find this...
Это аблитерированная сборка Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw, выполненная с еретиком, работающим непосредственно на квантованной модели EXL3. Вес EXL3 3.5bpw идентичен оригиналу....
EXL3 quantization of orcarouter/Qwen3.8-Flash-Next-Uncensored (BF16, tensor-level abliteration). 125B-A6B Qwen4-preview MoE at 2.05 bits per weight. All 512 experts...