// RUN ON CONSUMER GPU

Run OpenELM-3B 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 → ~915.8 yes 400k ~$1,999
NVIDIA GeForce RTX 4090 → ~515.1 yes 288k ~$1,599
NVIDIA GeForce RTX 3090 Ti → ~515.1 yes 288k ~$1,999
NVIDIA GeForce RTX 5080 → ~490.6 yes 176k ~$999
NVIDIA GeForce RTX 3090 → ~478.3 yes 288k ~$1,499
NVIDIA GeForce RTX 3080 Ti → ~466.1 yes 120k ~$1,199
NVIDIA GeForce RTX 5070 Ti → ~457.9 yes 176k ~$749
AMD Radeon RX 7900 XTX → ~434.2 yes 288k ~$999
NVIDIA GeForce RTX 3080 10GB → ~388.4 yes 92k ~$699
NVIDIA GeForce RTX 4080 → ~376.1 yes 176k ~$1,199
AMD Radeon RX 7900 XT → ~361.8 yes 232k ~$899
NVIDIA GeForce RTX 5070 → ~343.4 yes 120k ~$549
NVIDIA GeForce RTX 4070 Ti Super → ~343.4 yes 176k ~$799
NVIDIA GeForce RTX 3070 Ti → ~310.7 yes 63k ~$599
AMD Radeon RX 9070 XT → ~291.3 yes 176k ~$599
AMD Radeon RX 7800 XT → ~282.2 yes 176k ~$499
NVIDIA GeForce RTX 4070 Super → ~257.6 yes 120k ~$599
NVIDIA GeForce RTX 4070 → ~257.6 yes 120k ~$599
Intel Arc Pro B70 → ~257.1 yes 400k —
Intel Arc A770 16GB → ~236.8 yes 176k ~$329
AMD Radeon RX 6800 XT → ~231.6 yes 176k ~$649
AMD Radeon RX 6900 XT → ~231.6 yes 176k ~$999
NVIDIA GeForce RTX 3070 → ~228.9 yes 63k ~$499
NVIDIA GeForce RTX 5060 Ti 16GB → ~228.9 yes 176k ~$429
NVIDIA GeForce RTX 5060 Ti 8GB → ~228.9 yes 63k ~$379
Intel Arc Pro B60 → ~192.9 yes 288k —
Intel Arc B580 12GB → ~192.9 yes 120k ~$249
NVIDIA GeForce RTX 4060 Ti 8GB → ~147.2 yes 63k ~$399
NVIDIA GeForce RTX 4060 Ti 16GB → ~147.2 yes 176k ~$499
NVIDIA DGX Spark → ~139.5 yes 1709k ~$3,999
AMD Ryzen AI Max+ 395 → ~115.8 yes 1709k ~$1,999
Intel Arc Pro B50 → ~94.7 yes 176k —
NVIDIA GeForce RTX 2050 Mobile → ~57.2 tight 7k —

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

→ OpenELM-3B overview → All hardware

FAQ

What Consumer GPU hardware runs OpenELM-3B?▶

On GenAIList, 33 Consumer GPU options can run OpenELM-3B at Q4 — the fastest is the NVIDIA GeForce RTX 5090 at ~915.8 tok/s.

How fast is OpenELM-3B on Consumer GPU hardware?▶

Estimated generation speed ranges from ~57.2 to ~915.8 tok/s at Q4 (memory-bandwidth bound). Click any option for its full estimate and any measured numbers.