Qwen3.8-Flash-Next-Coder-cut240-GGUF
This GGUF requires the linked patched llama.cpp build; stock llama.cpp cannot load it. The model of Schiltmans/Qwen3.8-Flash-Next-Coder-cut240, packed...
This GGUF requires the linked patched llama.cpp build; stock llama.cpp cannot load it. The model of Schiltmans/Qwen3.8-Flash-Next-Coder-cut240, packed...
GLM-4.7-Flash with half of its routed experts removed by RAZOR, a training-free expert pruning method. Every MoE layer...
BF16 weights for CoderX — a code-targeted expert prune of Ornith-1.5-35B-A3B: 256 experts per layer reduced to 184,...
INVALID LANGUAGE PAIR SPECIFIED. EXAMPLE: LANGPAIR=EN|IT USING 2 LETTER ISO OR RFC3066 LIKE ZH-CN. ALMOST ALL LANGUAGES SUPPORTED...
GGUF quants of the 50%-REAP-pruned KAT-Coder-V2.5-Dev (Gated-DeltaNet + MoE hybrid): 256 → 128 experts, ~19B parameters, no MTP...
Straight talk first: if you have a 512 GiB machine, you don’t need this — the unpruned UD-IQ1S...
Kimi-K3-Audit-451E is Kimi K3 specialised for security auditing. It keeps 451 of the 896 routed experts in each...
DeepSeek-V4-Flash-0731 with its routed experts reduced from 256 to 132 per layer by router-weighted expert activation pruning (REAP),...
A GGUF quant of 0xSero/DeepSeek-V4-Flash-0731-REAP, the K160 expert-pruned checkpoint of deepseek-ai/DeepSeek-V4-Flash-0731. The pruning is 0xSero’s work: 160 of...
> Experimental research artifact. This is a 50% expert-pruned model, not an official Qwen release. The pruning calibration...