edtorre/ qwen3.6-hermes

27 5 days 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.

vision tools thinking

1 model

qwen3.6-hermes:latest
b046ba230ee2 • 18GB • 256K context window •
Text, Image input • 5 days ago