// RUN ON CONSUMER GPU

Run StableLM-3B-4E1T 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 → ~995.9 yes 402k ~$1,999
NVIDIA GeForce RTX 4090 → ~560.2 yes 290k ~$1,599
NVIDIA GeForce RTX 3090 Ti → ~560.2 yes 290k ~$1,999
NVIDIA GeForce RTX 5080 → ~533.5 yes 178k ~$999
NVIDIA GeForce RTX 3090 → ~520.2 yes 290k ~$1,499
NVIDIA GeForce RTX 3080 Ti → ~506.8 yes 122k ~$1,199
NVIDIA GeForce RTX 5070 Ti → ~498 yes 178k ~$749
AMD Radeon RX 7900 XTX → ~472.2 yes 290k ~$999
NVIDIA GeForce RTX 3080 10GB → ~422.4 yes 94k ~$699
NVIDIA GeForce RTX 4080 → ~409 yes 178k ~$1,199
AMD Radeon RX 7900 XT → ~393.5 yes 234k ~$899
NVIDIA GeForce RTX 5070 → ~373.5 yes 122k ~$549
NVIDIA GeForce RTX 4070 Ti Super → ~373.5 yes 178k ~$799
NVIDIA GeForce RTX 3070 Ti → ~337.9 yes 66k ~$599
AMD Radeon RX 9070 XT → ~316.8 yes 178k ~$599
AMD Radeon RX 7800 XT → ~306.9 yes 178k ~$499
NVIDIA GeForce RTX 4070 Super → ~280.1 yes 122k ~$599
NVIDIA GeForce RTX 4070 → ~280.1 yes 122k ~$599
Intel Arc Pro B70 → ~279.6 yes 402k —
Intel Arc A770 16GB → ~257.6 yes 178k ~$329
AMD Radeon RX 6800 XT → ~251.8 yes 178k ~$649
AMD Radeon RX 6900 XT → ~251.8 yes 178k ~$999
NVIDIA GeForce RTX 3070 → ~249 yes 66k ~$499
NVIDIA GeForce RTX 5060 Ti 16GB → ~249 yes 178k ~$429
NVIDIA GeForce RTX 5060 Ti 8GB → ~249 yes 66k ~$379
Intel Arc Pro B60 → ~209.7 yes 290k —
Intel Arc B580 12GB → ~209.7 yes 122k ~$249
NVIDIA GeForce RTX 4060 Ti 8GB → ~160.1 yes 66k ~$399
NVIDIA GeForce RTX 4060 Ti 16GB → ~160.1 yes 178k ~$499
NVIDIA DGX Spark → ~151.7 yes 1711k ~$3,999
AMD Ryzen AI Max+ 395 → ~125.9 yes 1711k ~$1,999
Intel Arc Pro B50 → ~103 yes 178k —
NVIDIA GeForce RTX 2050 Mobile → ~62.2 yes 9k —

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

→ StableLM-3B-4E1T overview → All hardware

FAQ

What Consumer GPU hardware runs StableLM-3B-4E1T?▶

On GenAIList, 33 Consumer GPU options can run StableLM-3B-4E1T at Q4 — the fastest is the NVIDIA GeForce RTX 5090 at ~995.9 tok/s.

How fast is StableLM-3B-4E1T on Consumer GPU hardware?▶

Estimated generation speed ranges from ~62.2 to ~995.9 tok/s at Q4 (memory-bandwidth bound). Click any option for its full estimate and any measured numbers.