Qwen 3.6 27B (Q4_K_M) optimized for Hermes Agent — 64K context, 8192 max tokens, MTP for speed, flash attention + Q8 KV cache.
260 Pulls 1 Tag Updated 2 weeks ago
Qwen3.6-35B uncensored flagship: 1M certified 70/70, vision, MTP grafted. One file, four capabilities.
1,856 Pulls 2 Tags Updated 3 weeks ago
Using 4096 tokens for flash attention context window to work as intended. Trying a new template and system prompt to see how it reacts.
123 Pulls 1 Tag Updated 11 months ago