Qwen: Qwen3.8 Max

n0404n0404/qwen3.6-finetune-qwen3.8-max-glm5.2-kimi-k3-distillation-a56-1168cb-heretic

635 Pulls 4 Tags Updated 1 month ago

edtorre/qwen3.6-hermes

Qwen 3.6 27B (Q4_K_M) optimized for Hermes Agent — 64K context, 8192 max tokens, MTP for speed, flash attention + Q8 KV cache.

vision tools thinking

893 Pulls 1 Tag Updated 2 months ago

mdq100/qwen3.5

Custom Qwen3.5 variants optimized for 128GB unified memory systems, such as AMD Ryzen AI Max+ 395. On Windows 11, GPU is limited to 96GB (32GB reserved for OS/CPU), requiring context window capped at 131072 tokens (128K) to fit within GPU memory limits.

vision tools thinking

449 Pulls 2 Tags Updated 5 months ago

orcarouter/Qwen3.8-27B-Uncensored

Qwen3.8-27B tensor-level abliterated, vision tower and MTP head untouched. 0% over-refusal on XSTest, 0-6% refusal across the A/B suite, no measurable capability loss. Full mmproj vision, tool calling and thinking, 262K context.

vision tools thinking

148.3K Pulls 20 Tags Updated 1 week ago

srchmnmichael/Qwen3.8-Uncensored

Qwen3.8-27B tensor-level abliterated, vision tower and MTP head untouched. 0% over-refusal on XSTest, 0-6% refusal across the A/B suite, no measurable capability loss. Full mmproj vision, tool calling and thinking, 262K context.

vision tools thinking

5,929 Pulls 4 Tags Updated 2 weeks ago

zdolny/qwen3-coder58k-tools

qwen3-coder with tools calling, context 58k to match full memory 31GB on RTX5090

tools

594 Pulls 1 Tag Updated 1 year ago