Is that on a single 3090? I need to change my settings it sounds like
Yes, single RTX 3090 with this model https://huggingface.co/llmfan46/Qwen3.6-35B-A3B-uncensored-h... following these https://huggingface.co/havenoammo/Qwen3.6-35B-A3B-MTP-GGUF instructions (should add "-j 8" to last cmake command for parallel build) and llama-server with --reasoning off
Note that the MTP PR https://github.com/ggml-org/llama.cpp/pull/22673 is still under development, so things might be broken.
alt Hacker News
Yes, single RTX 3090 with this model https://huggingface.co/llmfan46/Qwen3.6-35B-A3B-uncensored-h... following these https://huggingface.co/havenoammo/Qwen3.6-35B-A3B-MTP-GGUF instructions (should add "-j 8" to last cmake command for parallel build) and llama-server with --reasoning off
Note that the MTP PR https://github.com/ggml-org/llama.cpp/pull/22673 is still under development, so things might be broken.