Ready-to-serve Qwen3.8-Flash-Next and Qwen3.8-27B for capy-flash: one or two 16 GB RTX 50 GPUs, from 64 GB of RAM.
-
Feyd89/Qwen3.8-Flash-Next-NVFP4-capy-flash
Text Generation • Updated • 1.08k • 3 -
Feyd89/Qwen3.8-Flash-Next-GSQ-RCO-capy-flash
Text Generation • Updated • 1.18k • 1 -
Feyd89/Qwen3.8-Flash-Next-NVFP4-Vision-capy-flash
Image-Text-to-Text • Updated • 43 -
Feyd89/Qwen3.8-27B-GSQ-3bit-capy-flash
Image-Text-to-Text • Updated • 1.02k • 1