// RUN ON CONSUMER GPU

Run MiniCPM-2.4B 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 → ~1,140 yes 405k ~$1,999
NVIDIA GeForce RTX 4090 → ~641.3 yes 293k ~$1,599
NVIDIA GeForce RTX 3090 Ti → ~641.3 yes 293k ~$1,999
NVIDIA GeForce RTX 5080 → ~610.7 yes 181k ~$999
NVIDIA GeForce RTX 3090 → ~595.5 yes 293k ~$1,499
NVIDIA GeForce RTX 3080 Ti → ~580.2 yes 125k ~$1,199
NVIDIA GeForce RTX 5070 Ti → ~570 yes 181k ~$749
AMD Radeon RX 7900 XTX → ~540.5 yes 293k ~$999
NVIDIA GeForce RTX 3080 10GB → ~483.5 yes 97k ~$699
NVIDIA GeForce RTX 4080 → ~468.2 yes 181k ~$1,199
AMD Radeon RX 7900 XT → ~450.4 yes 237k ~$899
NVIDIA GeForce RTX 5070 → ~427.5 yes 125k ~$549
NVIDIA GeForce RTX 4070 Ti Super → ~427.5 yes 181k ~$799
NVIDIA GeForce RTX 3070 Ti → ~386.8 yes 69k ~$599
AMD Radeon RX 9070 XT → ~362.6 yes 181k ~$599
AMD Radeon RX 7800 XT → ~351.3 yes 181k ~$499
NVIDIA GeForce RTX 4070 Super → ~320.6 yes 125k ~$599
NVIDIA GeForce RTX 4070 → ~320.6 yes 125k ~$599
Intel Arc Pro B70 → ~320.1 yes 405k —
Intel Arc A770 16GB → ~294.8 yes 181k ~$329
AMD Radeon RX 6800 XT → ~288.3 yes 181k ~$649
AMD Radeon RX 6900 XT → ~288.3 yes 181k ~$999
NVIDIA GeForce RTX 3070 → ~285 yes 69k ~$499
NVIDIA GeForce RTX 5060 Ti 16GB → ~285 yes 181k ~$429
NVIDIA GeForce RTX 5060 Ti 8GB → ~285 yes 69k ~$379
Intel Arc Pro B60 → ~240.1 yes 293k —
Intel Arc B580 12GB → ~240.1 yes 125k ~$249
NVIDIA GeForce RTX 4060 Ti 8GB → ~183.2 yes 69k ~$399
NVIDIA GeForce RTX 4060 Ti 16GB → ~183.2 yes 181k ~$499
NVIDIA DGX Spark → ~173.7 yes 1714k ~$3,999
AMD Ryzen AI Max+ 395 → ~144.1 yes 1714k ~$1,999
Intel Arc Pro B50 → ~117.9 yes 181k —
NVIDIA GeForce RTX 2050 Mobile → ~71.3 yes 12k —

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

→ MiniCPM-2.4B overview → All hardware

FAQ

What Consumer GPU hardware runs MiniCPM-2.4B?▶

On GenAIList, 33 Consumer GPU options can run MiniCPM-2.4B at Q4 — the fastest is the NVIDIA GeForce RTX 5090 at ~1,140 tok/s.

How fast is MiniCPM-2.4B on Consumer GPU hardware?▶

Estimated generation speed ranges from ~71.3 to ~1,140 tok/s at Q4 (memory-bandwidth bound). Click any option for its full estimate and any measured numbers.