Smoffyy/Qwen3.6-27B-Instruct-Pure-GGUF
Image-Text-to-Text • 27B • Updated • 1.22k • 2
Qwen/Qwen3.6-27B
Latest Qwen 3.6 27B Family Pure GGUFs
Note VRAM usage ≈ 21gb on 32k token context length
Smoffyy/Qwen3.6-27B-Instruct-Revised-GGUF
Image-Text-to-Text • 27B • Updated • 2.42k • 3Note Jinja chat template revised version. Still pure, but cannot be listed as Pure by definition. (I recommend this one)