// RUN ON CONSUMER GPU

Run XLMR-XXL on Consumer GPU hardware

28 options ranked by estimated speed at Q4 / 8k context.

HardwareEst tok/sFits 8k?Max ctx~Price
NVIDIA GeForce RTX 5090 → ~260.2 yes 134k ~$1,999
NVIDIA GeForce RTX 4090 → ~146.4 yes 89k ~$1,599
NVIDIA GeForce RTX 3090 Ti → ~146.4 yes 89k ~$1,999
NVIDIA GeForce RTX 5080 → ~139.4 yes 44k ~$999
NVIDIA GeForce RTX 3090 → ~135.9 yes 89k ~$1,499
NVIDIA GeForce RTX 3080 Ti → ~132.4 yes 22k ~$1,199
NVIDIA GeForce RTX 5070 Ti → ~130.1 yes 44k ~$749
AMD Radeon RX 7900 XTX → ~123.4 yes 89k ~$999
NVIDIA GeForce RTX 3080 10GB → ~110.3 yes 10k ~$699
NVIDIA GeForce RTX 4080 → ~106.9 yes 44k ~$1,199
AMD Radeon RX 7900 XT → ~102.8 yes 67k ~$899
NVIDIA GeForce RTX 5070 → ~97.6 yes 22k ~$549
NVIDIA GeForce RTX 4070 Ti Super → ~97.6 yes 44k ~$799
AMD Radeon RX 9070 XT → ~82.8 yes 44k ~$599
AMD Radeon RX 7800 XT → ~80.2 yes 44k ~$499
NVIDIA GeForce RTX 4070 Super → ~73.2 yes 22k ~$599
NVIDIA GeForce RTX 4070 → ~73.2 yes 22k ~$599
Intel Arc Pro B70 → ~73.1 yes 134k —
Intel Arc A770 16GB → ~67.3 yes 44k ~$329
AMD Radeon RX 6800 XT → ~65.8 yes 44k ~$649
AMD Radeon RX 6900 XT → ~65.8 yes 44k ~$999
NVIDIA GeForce RTX 5060 Ti 16GB → ~65 yes 44k ~$429
Intel Arc Pro B60 → ~54.8 yes 89k —
Intel Arc B580 12GB → ~54.8 yes 22k ~$249
NVIDIA GeForce RTX 4060 Ti 16GB → ~41.8 yes 44k ~$499
NVIDIA DGX Spark → ~39.6 yes 657k ~$3,999
AMD Ryzen AI Max+ 395 → ~32.9 yes 657k ~$1,999
Intel Arc Pro B50 → ~26.9 yes 44k —

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

→ XLMR-XXL overview → All hardware

FAQ

What Consumer GPU hardware runs XLMR-XXL?▶

On GenAIList, 28 Consumer GPU options can run XLMR-XXL at Q4 — the fastest is the NVIDIA GeForce RTX 5090 at ~260.2 tok/s.

How fast is XLMR-XXL on Consumer GPU hardware?▶

Estimated generation speed ranges from ~26.9 to ~260.2 tok/s at Q4 (memory-bandwidth bound). Click any option for its full estimate and any measured numbers.