← AI Hashrate

Best GPUs for Coding LLMs

Our catalog tracks 7 coding LLMs (7.6B–480.2 parameters). For each, the table shows the cheapest retail GPU that fully fits it at Q4 / 8K context and the fastest retail GPU, with decode tok/s. Fit means weights + KV cache + 1 GB runtime overhead within 95% of VRAM — not weights alone. 1 of them exceed every retail GPU we track and are marked accordingly. Methodology.

#ModelParamsQ4/8K needs (GB)Best value GPU (fits)Fastest retail GPUBuy
1Qwen2.5-Coder-7B-Instruct7.6B6.7Arc B570 10GB ≈31.8 tok/s est.RTX 5090 32GB ≈150.0 tok/s est.Search Amazon (affiliate)
2Qwen2.5-Coder-14B-Instruct14.8B12.1RX 7600 XT 16GB ≈12.4 tok/s est.RTX 5090 32GB ≈77.1 tok/s est.Search Amazon (affiliate)
3Devstral-Small-250723.6B18.7RX 7900 XT 20GB ≈21.6 tok/s est.RTX 5090 32GB ≈48.3 tok/s est.Search Amazon (affiliate)
4Qwen3-Coder-30B-A3B-Instruct30.5B MoE 3B act.18.38RX 7900 XT 20GB ≈169.7 tok/s est.RTX 5090 32GB ≈380.1 tok/s est.Search Amazon (affiliate)
5Qwen2.5-Coder-32B-Instruct32.8B25.6Mac mini M4 32GB ≈2.3 tok/s est.RTX 5090 32GB ≈34.8 tok/s est.Search Amazon (affiliate)
6Qwen3-Coder-Next79.7B MoE 3B act.45.44Mac mini M4 Pro 64GB ≈57.9 tok/s est.RTX 6000 Ada 48GB ≈203.6 tok/s est.Search Amazon (affiliate)
7Qwen3-Coder-480B-A35B-Instruct480.2B MoE 35B act.272.11No retail GPU fits

est. = bandwidth-based estimate; measured = curated real benchmark that overrides the estimate. GPU names link to the full fit check (4K/8K/32K fit table + VRAM breakdown). MSRP is the launch list price, not live retail — Amazon prices change; click a Buy link for the current price. Models marked 'No retail GPU fits' need more VRAM than any retail card in our catalog (up to 192 GB) — see the model page for datacenter-class options.

Popular fit checks

Compare the picks

RTX 5090 32GB vs RX 7900 XT 20GB · Arc B570 10GB vs RTX 5090 32GB · Mac mini M4 32GB vs RTX 5090 32GB · Arc B570 10GB vs RX 7900 XT 20GB · Mac mini M4 32GB vs RX 7900 XT 20GB · Arc B570 10GB vs Mac mini M4 32GB

More lists: 7B-class models · 13B-class models · 30B-class models · 70B+ models · Under $500 · Under $1,000 · Under $2,000 · 8 GB VRAM · 12 GB VRAM · 16 GB VRAM · 24 GB VRAM · For Qwen3 · For DeepSeek · For Llama · For Gemma · For GLM · For reasoning · MoE picks