DeepSeek-v4-Flash-REAP-K180-NVFP4
REAP-pruned DeepSeek V4 Flash at K180 (180 routed experts per MoE layer, 30% pruning), with a hybrid mixed-precision...
REAP-pruned DeepSeek V4 Flash at K180 (180 routed experts per MoE layer, 30% pruning), with a hybrid mixed-precision...
REAP-pruned DeepSeek V4 Flash at K128 (128 routed experts per MoE layer). Prunes 50% of routed experts via...
GGUF of GLM-5.2, REAP expert-pruned (50%) + Q2K (~129 GB) — the maximum-context option for 2× 96 GB...
This repo contains three experimental IQ1M` GGUF quants derived from REAP-pruned Qwen 3.6 35B A3B checkpoints. I just...
This is a my second attempt on this model, which I hope to use as a local coder...
> [!TIP] > Support this work → · X · GitHub · REAP paper · Cerebras REAP 40%...
GGUF quantizations of 0xSero/gemma-4-19b-a4b-it-REAP, a 30% expert-pruned variant of google/gemma-4-26b-a4b-it using the REAP (Router-weighted Expert Activation Pruning) method....
> [!TIP] > Support this work → · X · GitHub · REAP paper · Cerebras REAP 20%...
> [!TIP] > Поддержите эту работу → · X · GitHub · REAP paper · Cerebras REAP В...
> [!TIP] > Support this work → · X · GitHub · REAP paper · Cerebras REAP W4A16...