| ▲ | eek2121 3 hours ago | |
Not really, Qwen 27b offloads to a decent gaming GPU (RTX 4090 in my case) without needing tons of RAM. | ||
| ▲ | mathisfun123 2 hours ago | parent [-] | |
can you give more info? llama.cpp vs vllm? config? i wanna try specifically this model | ||