// RUN ON CONSUMER GPU

Run Minitron 4B 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 → ~662.9 yes 390k ~$1,999
NVIDIA GeForce RTX 4090 → ~372.9 yes 278k ~$1,599
NVIDIA GeForce RTX 3090 Ti → ~372.9 yes 278k ~$1,999
NVIDIA GeForce RTX 5080 → ~355.1 yes 166k ~$999
NVIDIA GeForce RTX 3090 → ~346.2 yes 278k ~$1,499
NVIDIA GeForce RTX 3080 Ti → ~337.3 yes 110k ~$1,199
NVIDIA GeForce RTX 5070 Ti → ~331.4 yes 166k ~$749
AMD Radeon RX 7900 XTX → ~314.3 yes 278k ~$999
NVIDIA GeForce RTX 3080 10GB → ~281.1 yes 82k ~$699
NVIDIA GeForce RTX 4080 → ~272.2 yes 166k ~$1,199
AMD Radeon RX 7900 XT → ~261.9 yes 222k ~$899
NVIDIA GeForce RTX 5070 → ~248.6 yes 110k ~$549
NVIDIA GeForce RTX 4070 Ti Super → ~248.6 yes 166k ~$799
NVIDIA GeForce RTX 3070 Ti → ~224.9 yes 54k ~$599
AMD Radeon RX 9070 XT → ~210.8 yes 166k ~$599
AMD Radeon RX 7800 XT → ~204.3 yes 166k ~$499
NVIDIA GeForce RTX 4070 Super → ~186.4 yes 110k ~$599
NVIDIA GeForce RTX 4070 → ~186.4 yes 110k ~$599
Intel Arc Pro B70 → ~186.1 yes 390k —
Intel Arc A770 16GB → ~171.4 yes 166k ~$329
AMD Radeon RX 6800 XT → ~167.6 yes 166k ~$649
AMD Radeon RX 6900 XT → ~167.6 yes 166k ~$999
NVIDIA GeForce RTX 3070 → ~165.7 yes 54k ~$499
NVIDIA GeForce RTX 5060 Ti 16GB → ~165.7 yes 166k ~$429
NVIDIA GeForce RTX 5060 Ti 8GB → ~165.7 yes 54k ~$379
Intel Arc Pro B60 → ~139.6 yes 278k —
Intel Arc B580 12GB → ~139.6 yes 110k ~$249
NVIDIA GeForce RTX 4060 Ti 8GB → ~106.5 yes 54k ~$399
NVIDIA GeForce RTX 4060 Ti 16GB → ~106.5 yes 166k ~$499
NVIDIA DGX Spark → ~101 yes 1699k ~$3,999
AMD Ryzen AI Max+ 395 → ~83.8 yes 1699k ~$1,999
Intel Arc Pro B50 → ~68.6 yes 166k —

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

→ Minitron 4B overview → All hardware

FAQ

What Consumer GPU hardware runs Minitron 4B?▶

On GenAIList, 32 Consumer GPU options can run Minitron 4B at Q4 — the fastest is the NVIDIA GeForce RTX 5090 at ~662.9 tok/s.

How fast is Minitron 4B on Consumer GPU hardware?▶

Estimated generation speed ranges from ~68.6 to ~662.9 tok/s at Q4 (memory-bandwidth bound). Click any option for its full estimate and any measured numbers.