[model] add support for qwen3vl series by JJJYmmm · Pull Request #16780 · ggml-org/llama.cpp
github.com
This PR adds support for the Qwen3-VL series, including both the dense and MoE variants. The original implementation was contributed by @yairpatch and @Thireus (see #16207). @LETS-BEE also helped a...

Benchmarks look pretty good, even better than some of the text only models, make sure to take them with a grain of salt tho

Benchmarks

Qwen3 VL 30b a3b (No Thinking)

Visual benchmarks for Qwen3 VL 235 A22B (Thinking)