// RUN ON CONSUMER GPU

Run nekomata-14b on Consumer GPU hardware

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

HardwareEst tok/sFits 8k?Max ctx~Price
NVIDIA GeForce RTX 5090 → ~196.1 yes 122k ~$1,999
NVIDIA GeForce RTX 4090 → ~110.3 yes 77k ~$1,599
NVIDIA GeForce RTX 3090 Ti → ~110.3 yes 77k ~$1,999
NVIDIA GeForce RTX 5080 → ~105 yes 32k ~$999
NVIDIA GeForce RTX 3090 → ~102.4 yes 77k ~$1,499
NVIDIA GeForce RTX 3080 Ti → ~99.8 yes 10k ~$1,199
NVIDIA GeForce RTX 5070 Ti → ~98 yes 32k ~$749
AMD Radeon RX 7900 XTX → ~93 yes 77k ~$999
NVIDIA GeForce RTX 4080 → ~80.5 yes 32k ~$1,199
AMD Radeon RX 7900 XT → ~77.5 yes 55k ~$899
NVIDIA GeForce RTX 5070 → ~73.5 yes 10k ~$549
NVIDIA GeForce RTX 4070 Ti Super → ~73.5 yes 32k ~$799
AMD Radeon RX 9070 XT → ~62.4 yes 32k ~$599
AMD Radeon RX 7800 XT → ~60.4 yes 32k ~$499
Intel Arc Pro B70 → ~55.1 yes 122k —
NVIDIA GeForce RTX 4070 Super → ~55.1 yes 10k ~$599
NVIDIA GeForce RTX 4070 → ~55.1 yes 10k ~$599
Intel Arc A770 16GB → ~50.7 yes 32k ~$329
AMD Radeon RX 6800 XT → ~49.6 yes 32k ~$649
AMD Radeon RX 6900 XT → ~49.6 yes 32k ~$999
NVIDIA GeForce RTX 5060 Ti 16GB → ~49 yes 32k ~$429
Intel Arc Pro B60 → ~41.3 yes 77k —
Intel Arc B580 12GB → ~41.3 yes 10k ~$249
NVIDIA GeForce RTX 4060 Ti 16GB → ~31.5 yes 32k ~$499
NVIDIA DGX Spark → ~29.9 yes 645k ~$3,999
AMD Ryzen AI Max+ 395 → ~24.8 yes 645k ~$1,999
Intel Arc Pro B50 → ~20.3 yes 32k —

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

→ nekomata-14b overview → All hardware

FAQ

What Consumer GPU hardware runs nekomata-14b?▶

On GenAIList, 27 Consumer GPU options can run nekomata-14b at Q4 — the fastest is the NVIDIA GeForce RTX 5090 at ~196.1 tok/s.

How fast is nekomata-14b on Consumer GPU hardware?▶

Estimated generation speed ranges from ~20.3 to ~196.1 tok/s at Q4 (memory-bandwidth bound). Click any option for its full estimate and any measured numbers.