Smoffyy/Qwen3.5-4B-Instruct-Pure-GGUF
Image-Text-to-Text • 4B • Updated • 1.71k • 2
Qwen 3.5 4B Family Pure GGUFs
Note VRAM usage ≈ 7gb on 65k token context length
Note Jinja chat template revised version. Still pure, but cannot be listed as Pure by definition. (I recommend this one)