// RUN ON CONSUMER GPU

Run OpenELM-1.1B 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 → ~2,577.8 yes 417k ~$1,999
NVIDIA GeForce RTX 4090 → ~1,450 yes 305k ~$1,599
NVIDIA GeForce RTX 3090 Ti → ~1,450 yes 305k ~$1,999
NVIDIA GeForce RTX 5080 → ~1,381 yes 192k ~$999
NVIDIA GeForce RTX 3090 → ~1,346.4 yes 305k ~$1,499
NVIDIA GeForce RTX 3080 Ti → ~1,311.9 yes 136k ~$1,199
NVIDIA GeForce RTX 5070 Ti → ~1,288.9 yes 192k ~$749
AMD Radeon RX 7900 XTX → ~1,222.2 yes 305k ~$999
NVIDIA GeForce RTX 3080 10GB → ~1,093.3 yes 108k ~$699
NVIDIA GeForce RTX 4080 → ~1,058.7 yes 192k ~$1,199
AMD Radeon RX 7900 XT → ~1,018.5 yes 249k ~$899
NVIDIA GeForce RTX 5070 → ~966.7 yes 136k ~$549
NVIDIA GeForce RTX 4070 Ti Super → ~966.7 yes 192k ~$799
NVIDIA GeForce RTX 3070 Ti → ~874.6 yes 80k ~$599
AMD Radeon RX 9070 XT → ~819.9 yes 192k ~$599
AMD Radeon RX 7800 XT → ~794.4 yes 192k ~$499
NVIDIA GeForce RTX 4070 Super → ~725 yes 136k ~$599
NVIDIA GeForce RTX 4070 → ~725 yes 136k ~$599
Intel Arc Pro B70 → ~723.8 yes 417k —
Intel Arc A770 16GB → ~666.7 yes 192k ~$329
AMD Radeon RX 6800 XT → ~651.9 yes 192k ~$649
AMD Radeon RX 6900 XT → ~651.9 yes 192k ~$999
NVIDIA GeForce RTX 3070 → ~644.4 yes 80k ~$499
NVIDIA GeForce RTX 5060 Ti 16GB → ~644.4 yes 192k ~$429
NVIDIA GeForce RTX 5060 Ti 8GB → ~644.4 yes 80k ~$379
Intel Arc Pro B60 → ~542.9 yes 305k —
Intel Arc B580 12GB → ~542.9 yes 136k ~$249
NVIDIA GeForce RTX 4060 Ti 8GB → ~414.3 yes 80k ~$399
NVIDIA GeForce RTX 4060 Ti 16GB → ~414.3 yes 192k ~$499
NVIDIA DGX Spark → ~392.7 yes 1726k ~$3,999
AMD Ryzen AI Max+ 395 → ~325.9 yes 1726k ~$1,999
Intel Arc Pro B50 → ~266.7 yes 192k —
NVIDIA GeForce RTX 2050 Mobile → ~161.1 yes 24k —

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

→ OpenELM-1.1B overview → All hardware

FAQ

What Consumer GPU hardware runs OpenELM-1.1B?▶

On GenAIList, 33 Consumer GPU options can run OpenELM-1.1B at Q4 — the fastest is the NVIDIA GeForce RTX 5090 at ~2,577.8 tok/s.

How fast is OpenELM-1.1B on Consumer GPU hardware?▶

Estimated generation speed ranges from ~161.1 to ~2,577.8 tok/s at Q4 (memory-bandwidth bound). Click any option for its full estimate and any measured numbers.