KAT-Coder-V2.5-Dev-REAP-50-GGUF
GGUF quants of the 50%-REAP-pruned KAT-Coder-V2.5-Dev (Gated-DeltaNet + MoE hybrid): 256 → 128 experts, ~19B parameters, no MTP...
GGUF quants of the 50%-REAP-pruned KAT-Coder-V2.5-Dev (Gated-DeltaNet + MoE hybrid): 256 → 128 experts, ~19B parameters, no MTP...
This is the full-precision REAP-288 checkpoint. It is the 288-of-512 expert build spliced directly from the original bf16...
Straight talk first: if you have a 512 GiB machine, you don’t need this — the unpruned UD-IQ1S...
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...
A 9–10 GB mixture-of-experts specialist derived from google/gemma-4-26B-A4B-it by pruning 25 % of routed experts with routing-aware REAP...
Abliterated GGUF quant ladder of OpenMOSE/Qwen3.5-REAP-262B-A17B, itself a 34% REAP expert-pruning of Qwen3.5-397B-A17B down to 262B total /...
INVALID LANGUAGE PAIR SPECIFIED. EXAMPLE: LANGPAIR=EN|IT USING 2 LETTER ISO OR RFC3066 LIKE ZH-CN. ALMOST ALL LANGUAGES SUPPORTED...
> A 34%-expert-pruned GLM-5.2 that holds parity with the full unpruned model on a > well-powered real-world eval...
Qwen3.5-24.5B-Reapped-v1 is a model checkpoint packaged for compatible Hugging Face runtimes, published by groxaxo. It is intended for...