Qwen3.6 MTP — Crucible release Collection MTP NextN GGUF for Qwen3.5/3.6 — IMAT, Q8nextn override, llama.cpp crucible-mtp fork. 4B/27B/35B-A3B, IQ4_XS+Q4_K_M+Q5_K_M. • 6 items • Updated 20 days ago • 3
EXL2 Tool Calling Model Quants Collection A collection of tool calling models quanted for EXL2 by yours truly • 7 items • Updated Jul 18, 2024 • 1
Cerebras REAP Collection Sparse MoE models compressed using REAP (Router-weighted Expert Activation Pruning) method • 30 items • Updated Feb 25 • 141