// RUN ON CONSUMER GPU

Run Ministral 8B on Consumer GPU hardware

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

HardwareEst tok/sFits 8k?Max ctx~Price
NVIDIA GeForce RTX 5090 → ~348 yes 179k ~$1,999
NVIDIA GeForce RTX 4090 → ~195.8 yes 123k ~$1,599
NVIDIA GeForce RTX 3090 Ti → ~195.8 yes 123k ~$1,999
NVIDIA GeForce RTX 5080 → ~186.4 yes 67k ~$999
NVIDIA GeForce RTX 3090 → ~181.8 yes 123k ~$1,499
NVIDIA GeForce RTX 3080 Ti → ~177.1 yes 39k ~$1,199
NVIDIA GeForce RTX 5070 Ti → ~174 yes 67k ~$749
AMD Radeon RX 7900 XTX → ~165 yes 123k ~$999
NVIDIA GeForce RTX 3080 10GB → ~147.6 yes 25k ~$699
NVIDIA GeForce RTX 4080 → ~142.9 yes 67k ~$1,199
AMD Radeon RX 7900 XT → ~137.5 yes 95k ~$899
NVIDIA GeForce RTX 5070 → ~130.5 yes 39k ~$549
NVIDIA GeForce RTX 4070 Ti Super → ~130.5 yes 67k ~$799
NVIDIA GeForce RTX 3070 Ti → ~118.1 yes 11k ~$599
AMD Radeon RX 9070 XT → ~110.7 yes 67k ~$599
AMD Radeon RX 7800 XT → ~107.3 yes 67k ~$499
NVIDIA GeForce RTX 4070 Super → ~97.9 yes 39k ~$599
NVIDIA GeForce RTX 4070 → ~97.9 yes 39k ~$599
Intel Arc Pro B70 → ~97.7 yes 179k —
Intel Arc A770 16GB → ~90 yes 67k ~$329
AMD Radeon RX 6800 XT → ~88 yes 67k ~$649
AMD Radeon RX 6900 XT → ~88 yes 67k ~$999
NVIDIA GeForce RTX 3070 → ~87 yes 11k ~$499
NVIDIA GeForce RTX 5060 Ti 16GB → ~87 yes 67k ~$429
NVIDIA GeForce RTX 5060 Ti 8GB → ~87 yes 11k ~$379
Intel Arc Pro B60 → ~73.3 yes 123k —
Intel Arc B580 12GB → ~73.3 yes 39k ~$249
NVIDIA GeForce RTX 4060 Ti 8GB → ~55.9 yes 11k ~$399
NVIDIA GeForce RTX 4060 Ti 16GB → ~55.9 yes 67k ~$499
NVIDIA DGX Spark → ~53 yes 833k ~$3,999
AMD Ryzen AI Max+ 395 → ~44 yes 833k ~$1,999
Intel Arc Pro B50 → ~36 yes 67k —

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

→ Ministral 8B overview → All hardware

FAQ

What Consumer GPU hardware runs Ministral 8B?▶

On GenAIList, 32 Consumer GPU options can run Ministral 8B at Q4 — the fastest is the NVIDIA GeForce RTX 5090 at ~348 tok/s.

How fast is Ministral 8B on Consumer GPU hardware?▶

Estimated generation speed ranges from ~36 to ~348 tok/s at Q4 (memory-bandwidth bound). Click any option for its full estimate and any measured numbers.