LLM Inference Speed
SmolLM-135M.Q4_K_M
SmolLM-135M.Q4_K_M
qwen1_5-0_5b-chat-q4_k_m
gemma-2b.Q4_K_M
llama-7b.Q4_K_M
phi-4-q4
Llama-3.3-70B-Instruct-Q4_K_M
Learn more about
this comparison