2,256 Pulls 1 Tag Updated 4 weeks ago
Qwen 3.6 27B (Q4_K_M) optimized for Hermes Agent — 64K context, 8192 max tokens, MTP for speed, flash attention + Q8 KV cache.
812 Pulls 1 Tag Updated 1 month ago
maximum 256k context length for coding and other long-context tasks
871 Pulls 1 Tag Updated 11 months ago