Qwen3.8-27B latent attention retrofits Collection Training-free MLA / GLA retrofits of Qwen3.8-27B with a 2x smaller KV cache. Weights preview; vLLM plugin, quants and code coming early October 2026. • 8 items • Updated Oct 15 • 6
ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF Image-Text-to-Text • 177B • Updated Sep 29 • 7.16M • 1.27k
huihui-ai/Huihui-Qwen3.8-Flash-Next-abliterated-GGUF Image-Text-to-Text • 177B • Updated Oct 11 • 232k • 214
GSQ-RCO-GGUF Collection Non-uniform GGUF quantizations via GSQ + RCO: per-tensor mixed precision in standard GGUF form • 5 items • Updated 13 days ago • 110
TelperionAI/Qwen3.8-27B-NVFP4-AWQ-AutoRound-allfp4 Image-Text-to-Text • 19B • Updated Sep 3 • 158 • 5