// RUN ON CONSUMER GPU

Run ProteinLM on Consumer GPU hardware

33 options ranked by estimated speed at Q4 / 8k context.

HardwareEst tok/sFits 8k?Max ctx~Price
NVIDIA GeForce RTX 5090 → ~928 yes 401k ~$1,999
NVIDIA GeForce RTX 4090 → ~522 yes 288k ~$1,599
NVIDIA GeForce RTX 3090 Ti → ~522 yes 288k ~$1,999
NVIDIA GeForce RTX 5080 → ~497.1 yes 176k ~$999
NVIDIA GeForce RTX 3090 → ~484.7 yes 288k ~$1,499
NVIDIA GeForce RTX 3080 Ti → ~472.3 yes 120k ~$1,199
NVIDIA GeForce RTX 5070 Ti → ~464 yes 176k ~$749
AMD Radeon RX 7900 XTX → ~440 yes 288k ~$999
NVIDIA GeForce RTX 3080 10GB → ~393.6 yes 92k ~$699
NVIDIA GeForce RTX 4080 → ~381.1 yes 176k ~$1,199
AMD Radeon RX 7900 XT → ~366.7 yes 232k ~$899
NVIDIA GeForce RTX 5070 → ~348 yes 120k ~$549
NVIDIA GeForce RTX 4070 Ti Super → ~348 yes 176k ~$799
NVIDIA GeForce RTX 3070 Ti → ~314.9 yes 64k ~$599
AMD Radeon RX 9070 XT → ~295.2 yes 176k ~$599
AMD Radeon RX 7800 XT → ~286 yes 176k ~$499
NVIDIA GeForce RTX 4070 Super → ~261 yes 120k ~$599
NVIDIA GeForce RTX 4070 → ~261 yes 120k ~$599
Intel Arc Pro B70 → ~260.6 yes 401k —
Intel Arc A770 16GB → ~240 yes 176k ~$329
AMD Radeon RX 6800 XT → ~234.7 yes 176k ~$649
AMD Radeon RX 6900 XT → ~234.7 yes 176k ~$999
NVIDIA GeForce RTX 3070 → ~232 yes 64k ~$499
NVIDIA GeForce RTX 5060 Ti 16GB → ~232 yes 176k ~$429
NVIDIA GeForce RTX 5060 Ti 8GB → ~232 yes 64k ~$379
Intel Arc Pro B60 → ~195.4 yes 288k —
Intel Arc B580 12GB → ~195.4 yes 120k ~$249
NVIDIA GeForce RTX 4060 Ti 8GB → ~149.1 yes 64k ~$399
NVIDIA GeForce RTX 4060 Ti 16GB → ~149.1 yes 176k ~$499
NVIDIA DGX Spark → ~141.4 yes 1709k ~$3,999
AMD Ryzen AI Max+ 395 → ~117.3 yes 1709k ~$1,999
Intel Arc Pro B50 → ~96 yes 176k —
NVIDIA GeForce RTX 2050 Mobile → ~58 tight 8k —

Estimate at Q4 (memory-bound). Click any option for its full per-hardware estimate and measured numbers.

→ ProteinLM overview → All hardware

FAQ

What Consumer GPU hardware runs ProteinLM?▶

On GenAIList, 33 Consumer GPU options can run ProteinLM at Q4 — the fastest is the NVIDIA GeForce RTX 5090 at ~928 tok/s.

How fast is ProteinLM on Consumer GPU hardware?▶

Estimated generation speed ranges from ~58 to ~928 tok/s at Q4 (memory-bandwidth bound). Click any option for its full estimate and any measured numbers.