Qwen 3.6 27B (Q4_K_M) optimized for Hermes Agent — 64K context, 8192 max tokens, MTP for speed, flash attention + Q8 KV cache.
904 Pulls 1 Tag Updated 2 months ago
Qwen3.6-35B uncensored flagship: 1M certified 70/70, vision, MTP grafted. One file, four capabilities.
3,797 Pulls 2 Tags Updated 2 months 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.
129 Pulls 1 Tag Updated 1 year ago