// RUN ON CONSUMER GPU

Run BLOOM-7.1B 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 → ~393.8 yes 183k ~$1,999
NVIDIA GeForce RTX 4090 → ~221.5 yes 127k ~$1,599
NVIDIA GeForce RTX 3090 Ti → ~221.5 yes 127k ~$1,999
NVIDIA GeForce RTX 5080 → ~211 yes 71k ~$999
NVIDIA GeForce RTX 3090 → ~205.7 yes 127k ~$1,499
NVIDIA GeForce RTX 3080 Ti → ~200.4 yes 43k ~$1,199
NVIDIA GeForce RTX 5070 Ti → ~196.9 yes 71k ~$749
AMD Radeon RX 7900 XTX → ~186.7 yes 127k ~$999
NVIDIA GeForce RTX 3080 10GB → ~167 yes 29k ~$699
NVIDIA GeForce RTX 4080 → ~161.7 yes 71k ~$1,199
AMD Radeon RX 7900 XT → ~155.6 yes 99k ~$899
NVIDIA GeForce RTX 5070 → ~147.7 yes 43k ~$549
NVIDIA GeForce RTX 4070 Ti Super → ~147.7 yes 71k ~$799
NVIDIA GeForce RTX 3070 Ti → ~133.6 yes 15k ~$599
AMD Radeon RX 9070 XT → ~125.2 yes 71k ~$599
AMD Radeon RX 7800 XT → ~121.4 yes 71k ~$499
NVIDIA GeForce RTX 4070 Super → ~110.7 yes 43k ~$599
NVIDIA GeForce RTX 4070 → ~110.7 yes 43k ~$599
Intel Arc Pro B70 → ~110.6 yes 183k —
Intel Arc A770 16GB → ~101.8 yes 71k ~$329
AMD Radeon RX 6800 XT → ~99.6 yes 71k ~$649
AMD Radeon RX 6900 XT → ~99.6 yes 71k ~$999
NVIDIA GeForce RTX 3070 → ~98.4 yes 15k ~$499
NVIDIA GeForce RTX 5060 Ti 16GB → ~98.4 yes 71k ~$429
NVIDIA GeForce RTX 5060 Ti 8GB → ~98.4 yes 15k ~$379
Intel Arc Pro B60 → ~82.9 yes 127k —
Intel Arc B580 12GB → ~82.9 yes 43k ~$249
NVIDIA GeForce RTX 4060 Ti 8GB → ~63.3 yes 15k ~$399
NVIDIA GeForce RTX 4060 Ti 16GB → ~63.3 yes 71k ~$499
NVIDIA DGX Spark → ~60 yes 837k ~$3,999
AMD Ryzen AI Max+ 395 → ~49.8 yes 837k ~$1,999
Intel Arc Pro B50 → ~40.7 yes 71k —

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

→ BLOOM-7.1B overview → All hardware

FAQ

What Consumer GPU hardware runs BLOOM-7.1B?▶

On GenAIList, 32 Consumer GPU options can run BLOOM-7.1B at Q4 — the fastest is the NVIDIA GeForce RTX 5090 at ~393.8 tok/s.

How fast is BLOOM-7.1B on Consumer GPU hardware?▶

Estimated generation speed ranges from ~40.7 to ~393.8 tok/s at Q4 (memory-bandwidth bound). Click any option for its full estimate and any measured numbers.