Pick the local model that fits your GPU.

FAQ

Which local LLM should I run on a 24GB GPU?

On RTX 4090 24GB, the current Code Generation + Quality profile ranks Qwen3 Coder 30B-A3B (3B active / 30.5B MoE, Q8_0, Partial offload) first. The largest current full-GPU recommendation in that profile is Codestral 22B (22B dense, Q8_0, Full GPU). The nearest 70B-class recommendation is Llama 3.3 70B (70B dense, Q4_K_M, Partial offload), so treat that as a quality/offload pick instead of the default for fast loops.

What is the best quantization for local LLMs?

The picker does not use one universal best quantization. On the same RTX 4090 24GB reference setup, Code Generation + Quality currently chooses Q8_0 for Qwen3 Coder 30B-A3B, Chat/Assistant + Speed chooses IQ3_XXS for Qwen3 Coder 30B-A3B, and Chat/Assistant + VRAM Efficiency chooses IQ4_XS for Phi-4-mini. Those claims come from the ranked catalog plus the VRAM fit estimate at 4,096 tokens.

Should I pick the fastest model or the highest quality model?

Use Speed when tokens per second matters; the current reference winner is Qwen3 Coder 30B-A3B (3B active / 30.5B MoE, IQ3_XXS, Full GPU) at 67.6-129.9 tok/s. Use Quality when model strength matters more; the current reference winner is Qwen3 Coder 30B-A3B (3B active / 30.5B MoE, Q8_0, Partial offload) at 32.4-62.3 tok/s. Use VRAM Efficiency when keeping the model on one GPU matters; the current reference winner is Phi-4-mini (3.8B dense, IQ4_XS, Full GPU) at 55.3-106.3 tok/s.