// RUN ON CONSUMER GPU

Run BELLE-LLaMA-13B-2M-enc 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 → ~214.2 yes 126k ~$1,999
NVIDIA GeForce RTX 4090 → ~120.5 yes 81k ~$1,599
NVIDIA GeForce RTX 3090 Ti → ~120.5 yes 81k ~$1,999
NVIDIA GeForce RTX 5080 → ~114.7 yes 36k ~$999
NVIDIA GeForce RTX 3090 → ~111.9 yes 81k ~$1,499
NVIDIA GeForce RTX 3080 Ti → ~109 yes 14k ~$1,199
NVIDIA GeForce RTX 5070 Ti → ~107.1 yes 36k ~$749
AMD Radeon RX 7900 XTX → ~101.5 yes 81k ~$999
NVIDIA GeForce RTX 3080 10GB → ~90.8 tight 3k ~$699
NVIDIA GeForce RTX 4080 → ~88 yes 36k ~$1,199
AMD Radeon RX 7900 XT → ~84.6 yes 59k ~$899
NVIDIA GeForce RTX 5070 → ~80.3 yes 14k ~$549
NVIDIA GeForce RTX 4070 Ti Super → ~80.3 yes 36k ~$799
AMD Radeon RX 9070 XT → ~68.1 yes 36k ~$599
AMD Radeon RX 7800 XT → ~66 yes 36k ~$499
NVIDIA GeForce RTX 4070 Super → ~60.2 yes 14k ~$599
NVIDIA GeForce RTX 4070 → ~60.2 yes 14k ~$599
Intel Arc Pro B70 → ~60.1 yes 126k —
Intel Arc A770 16GB → ~55.4 yes 36k ~$329
AMD Radeon RX 6800 XT → ~54.2 yes 36k ~$649
AMD Radeon RX 6900 XT → ~54.2 yes 36k ~$999
NVIDIA GeForce RTX 5060 Ti 16GB → ~53.5 yes 36k ~$429
Intel Arc Pro B60 → ~45.1 yes 81k —
Intel Arc B580 12GB → ~45.1 yes 14k ~$249
NVIDIA GeForce RTX 4060 Ti 16GB → ~34.4 yes 36k ~$499
NVIDIA DGX Spark → ~32.6 yes 650k ~$3,999
AMD Ryzen AI Max+ 395 → ~27.1 yes 650k ~$1,999
Intel Arc Pro B50 → ~22.2 yes 36k —

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

→ BELLE-LLaMA-13B-2M-enc overview → All hardware

FAQ

What Consumer GPU hardware runs BELLE-LLaMA-13B-2M-enc?▶

On GenAIList, 28 Consumer GPU options can run BELLE-LLaMA-13B-2M-enc at Q4 — the fastest is the NVIDIA GeForce RTX 5090 at ~214.2 tok/s.

How fast is BELLE-LLaMA-13B-2M-enc on Consumer GPU hardware?▶

Estimated generation speed ranges from ~22.2 to ~214.2 tok/s at Q4 (memory-bandwidth bound). Click any option for its full estimate and any measured numbers.