// RUN ON CONSUMER GPU

Run CodeGen-Mono 16.1B on Consumer GPU hardware

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

HardwareEst tok/sFits 8k?Max ctx~Price
NVIDIA GeForce RTX 5090 → ~172.9 yes 72k ~$1,999
NVIDIA GeForce RTX 4090 → ~97.3 yes 44k ~$1,599
NVIDIA GeForce RTX 3090 Ti → ~97.3 yes 44k ~$1,999
NVIDIA GeForce RTX 5080 → ~92.6 yes 16k ~$999
NVIDIA GeForce RTX 3090 → ~90.3 yes 44k ~$1,499
NVIDIA GeForce RTX 5070 Ti → ~86.5 yes 16k ~$749
AMD Radeon RX 7900 XTX → ~82 yes 44k ~$999
NVIDIA GeForce RTX 4080 → ~71 yes 16k ~$1,199
AMD Radeon RX 7900 XT → ~68.3 yes 30k ~$899
NVIDIA GeForce RTX 4070 Ti Super → ~64.8 yes 16k ~$799
AMD Radeon RX 9070 XT → ~55 yes 16k ~$599
AMD Radeon RX 7800 XT → ~53.3 yes 16k ~$499
Intel Arc Pro B70 → ~48.6 yes 72k —
Intel Arc A770 16GB → ~44.7 yes 16k ~$329
AMD Radeon RX 6800 XT → ~43.7 yes 16k ~$649
AMD Radeon RX 6900 XT → ~43.7 yes 16k ~$999
NVIDIA GeForce RTX 5060 Ti 16GB → ~43.2 yes 16k ~$429
Intel Arc Pro B60 → ~36.4 yes 44k —
NVIDIA GeForce RTX 4060 Ti 16GB → ~27.8 yes 16k ~$499
NVIDIA DGX Spark → ~26.3 yes 399k ~$3,999
AMD Ryzen AI Max+ 395 → ~21.9 yes 399k ~$1,999
Intel Arc Pro B50 → ~17.9 yes 16k —

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

→ CodeGen-Mono 16.1B overview → All hardware

FAQ

What Consumer GPU hardware runs CodeGen-Mono 16.1B?▶

On GenAIList, 22 Consumer GPU options can run CodeGen-Mono 16.1B at Q4 — the fastest is the NVIDIA GeForce RTX 5090 at ~172.9 tok/s.

How fast is CodeGen-Mono 16.1B on Consumer GPU hardware?▶

Estimated generation speed ranges from ~17.9 to ~172.9 tok/s at Q4 (memory-bandwidth bound). Click any option for its full estimate and any measured numbers.