deepseek-v4-flash-reap-k128-Q2-Q4-Mixed-GGUF
REAP-pruned DeepSeek V4 Flash at K128 (128 routed experts per MoE layer). Prunes 50% of routed experts via...
REAP-pruned DeepSeek V4 Flash at K128 (128 routed experts per MoE layer). Prunes 50% of routed experts via...
Gemma3.5-48B-A4B-Q4KM is a community-built GGUF release that combines the instruction behavior of Gemma 3 27B with the Gemma...
LFM 8B-1A8 (MOE, 32 эксперта), обученный пользовательскому набору ДАННЫХ с использованием Qwen 3.6 35B-A3B (MOE, 256 экспертов, в...
Base model: google/gemma-4-26b-it Architecture: MoE — 26B total / ≈4B active parameters (1 shared expert + 8 routed...
MXFP4MOE** GGUF quantization of Qwen3.6-35B-A3B, Alibaba Cloud’s efficient 35B MoE multimodal foundation model (3B activated) with 262K context,...
Surge-Cognition-4x8B is an experimental Mixture-of-Experts (MoE) language model focused on reasoning, coding, medical understanding, and general conversational intelligence....
GGUF quantizations of Jackrong/Qwopus3.6-35B-A3B-v1 for use with llama.cpp and compatible runtimes. > 📎 Vision support: Place mmproj.gguf in...
weighted/imatrix quants of https://huggingface.co/Youssofal/Qwen3.6-35B-A3B-Abliterated-Heretic-BF16 For a convenient overview and download list, visit our model page for this model....
Faithful small-scale (~3.2B total / ~1.10B activated per token) replica of the DeepSeek-V4 architecture, sized to be trainable...
INVALID LANGUAGE PAIR SPECIFIED. EXAMPLE: LANGPAIR=EN|IT USING 2 LETTER ISO OR RFC3066 LIKE ZH-CN. ALMOST ALL LANGUAGES SUPPORTED...