// RUN ON CONSUMER GPU

Run Minitron 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 → ~335.4 yes 178k ~$1,999
NVIDIA GeForce RTX 4090 → ~188.7 yes 122k ~$1,599
NVIDIA GeForce RTX 3090 Ti → ~188.7 yes 122k ~$1,999
NVIDIA GeForce RTX 5080 → ~179.7 yes 65k ~$999
NVIDIA GeForce RTX 3090 → ~175.2 yes 122k ~$1,499
NVIDIA GeForce RTX 3080 Ti → ~170.7 yes 37k ~$1,199
NVIDIA GeForce RTX 5070 Ti → ~167.7 yes 65k ~$749
AMD Radeon RX 7900 XTX → ~159 yes 122k ~$999
NVIDIA GeForce RTX 3080 10GB → ~142.3 yes 23k ~$699
NVIDIA GeForce RTX 4080 → ~137.8 yes 65k ~$1,199
AMD Radeon RX 7900 XT → ~132.5 yes 93k ~$899
NVIDIA GeForce RTX 5070 → ~125.8 yes 37k ~$549
NVIDIA GeForce RTX 4070 Ti Super → ~125.8 yes 65k ~$799
NVIDIA GeForce RTX 3070 Ti → ~113.8 yes 9k ~$599
AMD Radeon RX 9070 XT → ~106.7 yes 65k ~$599
AMD Radeon RX 7800 XT → ~103.4 yes 65k ~$499
NVIDIA GeForce RTX 4070 Super → ~94.3 yes 37k ~$599
NVIDIA GeForce RTX 4070 → ~94.3 yes 37k ~$599
Intel Arc Pro B70 → ~94.2 yes 178k —
Intel Arc A770 16GB → ~86.7 yes 65k ~$329
AMD Radeon RX 6800 XT → ~84.8 yes 65k ~$649
AMD Radeon RX 6900 XT → ~84.8 yes 65k ~$999
NVIDIA GeForce RTX 3070 → ~83.9 yes 9k ~$499
NVIDIA GeForce RTX 5060 Ti 16GB → ~83.9 yes 65k ~$429
NVIDIA GeForce RTX 5060 Ti 8GB → ~83.9 yes 9k ~$379
Intel Arc Pro B60 → ~70.6 yes 122k —
Intel Arc B580 12GB → ~70.6 yes 37k ~$249
NVIDIA GeForce RTX 4060 Ti 8GB → ~53.9 yes 9k ~$399
NVIDIA GeForce RTX 4060 Ti 16GB → ~53.9 yes 65k ~$499
NVIDIA DGX Spark → ~51.1 yes 832k ~$3,999
AMD Ryzen AI Max+ 395 → ~42.4 yes 832k ~$1,999
Intel Arc Pro B50 → ~34.7 yes 65k —

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

→ Minitron 8B overview → All hardware

FAQ

What Consumer GPU hardware runs Minitron 8B?▶

On GenAIList, 32 Consumer GPU options can run Minitron 8B at Q4 — the fastest is the NVIDIA GeForce RTX 5090 at ~335.4 tok/s.

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

Estimated generation speed ranges from ~34.7 to ~335.4 tok/s at Q4 (memory-bandwidth bound). Click any option for its full estimate and any measured numbers.