Views
No views yet
--mmproj flag in llama.cpp.| Property | Value |
|---|---|
| Base Model | AEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored-BF16 |
| Tensors | 334 (27 ViT blocks + merger + patch embed + position embed) |
| File Size | 931 MB |
| Extracted From | BF16 original model |
1llama-server \
2 -m qwen3.6-27b-Q6K-mtp.gguf \
3 --mmproj qwen3.6-27b-mmproj.gguf \
4 -ngl 99 \
5 -c 80000 \
6 --host 0.0.0.0 \
7 --port 8080 \
8 --spec-type draft-mtp