SmolVLM2-2.2B-Instruct
Original model: https://huggingface.co/HuggingFaceTB/SmolVLM2-2.2B-Instruct
For more info, please refer to this PR: https://github.com/ggml-org/llama.cpp/pull/13050
Original model: https://huggingface.co/HuggingFaceTB/SmolVLM2-2.2B-Instruct
For more info, please refer to this PR: https://github.com/ggml-org/llama.cpp/pull/13050
LocalMaxxingLD_LIBRARY_PATH=/home/beta1/qwen38-release/tools/llama-b10442-cuda /home/beta1/qwen38-release/tools/llama-b10442-cuda/llama-bench -m /mnt/pf/pf-deep2/SmolVLM2-2.2B-Instruct-GGUF/SmolVLM2-2.2B-Instruct-Q4_K_M.gguf -p 512 -n 128 -ngl 99 -fa 1在 LocalMaxxing 上查看测试
来自 LocalMaxxing 的 1 次社区测试（1 种配置）的中位数。
自己运行：配置指南