Qwen3.8 Max · Ollama

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

770 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

945 Pulls 1 Tag Updated 2 months ago

aiconjured/Qwen3.8-27B-FableColdFusion-735882-HereticUncensored-NEOCODERMAX-MTP-NVFP4-Q8-Q3

Text + Vision Qwen3.8-27B-FableColdFusion-735882-HereticUncensored-NEOCODERMAX-MTP-NVFP4-Q8-Q3

vision

616 Pulls 1 Tag Updated 1 week 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

465 Pulls 2 Tags Updated 6 months 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

6,854 Pulls 4 Tags Updated 3 weeks 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

186.9K Pulls 20 Tags Updated 3 weeks ago

aratan/qwen3.8

Contexto muy pequeño para agentes, SOLO chat. y 5 t/s en RTX 4060

vision tools thinking

45 Pulls 1 Tag Updated 1 month 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

aiconjured/Qwen3.8-27B-NVFP4-MTP-COMPACT-LOW

Text + Vision All credit: https://huggingface.co/esatapedico/Qwen3.8-27B-NVFP4-MTP-GGUF

vision

265 Pulls 1 Tag Updated 4 weeks ago

rafw007/qwen3-coder-next-80b-redteam

Validated runtime configuration + measured results for an abliterated (uncensored) Qwen3-Coder-Next 80B-A3B running as an agentic coding backend on CPU via ik_llama.cpp

519 Pulls 1 Tag Updated 9 hours ago