Name and Version

./llama-cli --version
version: 9204 (726704a)
built with GNU 11.4.0 for Linux x86_64

./llama-server -hf unsloth/Qwen3.6-27B-MTP-GGUF:Q4_K_M --threads -1 --parallel 1 --ctx-size 16384 --temp 0.7 --min-p 0.0 --top-p 0.8 --top-k 20 --presence-penalty 1.5 --predict 4096 --reasoning off --direct-io --no-mmproj
Downloading mmproj-BF16.gguf ──╴                                       6%
Downloading Qwen3.6-27B-Q4_K_M.gguf                                    0%

If --no-mmproj parameter is given, I'm expecting to skip downloading mmproj file.

Operating systems

Linux

GGML backends

Vulkan

Hardware

AMD 7840U

Models

No response

Problem description & steps to reproduce

./llama-server -hf unsloth/Qwen3.6-27B-MTP-GGUF:Q4_K_M --threads -1 --parallel 1 --ctx-size 16384 --temp 0.7 --min-p 0.0 --top-p 0.8 --top-k 20 --presence-penalty 1.5 --predict 4096 --reasoning off --direct-io --no-mmproj

First Bad Commit

No response

Relevant log output

Downloading mmproj-BF16.gguf ──╴ 6%