// RUN ON CONSUMER GPU

Run Zagreus 0.4B 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 → ~6,960 yes 423k ~$1,999
NVIDIA GeForce RTX 4090 → ~3,915 yes 311k ~$1,599
NVIDIA GeForce RTX 3090 Ti → ~3,915 yes 311k ~$1,999
NVIDIA GeForce RTX 5080 → ~3,728.6 yes 198k ~$999
NVIDIA GeForce RTX 3090 → ~3,635.4 yes 311k ~$1,499
NVIDIA GeForce RTX 3080 Ti → ~3,542.1 yes 142k ~$1,199
NVIDIA GeForce RTX 5070 Ti → ~3,480 yes 198k ~$749
AMD Radeon RX 7900 XTX → ~3,300 yes 311k ~$999
NVIDIA GeForce RTX 3080 10GB → ~2,951.8 yes 114k ~$699
NVIDIA GeForce RTX 4080 → ~2,858.6 yes 198k ~$1,199
AMD Radeon RX 7900 XT → ~2,750 yes 254k ~$899
NVIDIA GeForce RTX 5070 → ~2,610 yes 142k ~$549
NVIDIA GeForce RTX 4070 Ti Super → ~2,610 yes 198k ~$799
NVIDIA GeForce RTX 3070 Ti → ~2,361.4 yes 86k ~$599
AMD Radeon RX 9070 XT → ~2,213.8 yes 198k ~$599
AMD Radeon RX 7800 XT → ~2,145 yes 198k ~$499
NVIDIA GeForce RTX 4070 Super → ~1,957.5 yes 142k ~$599
NVIDIA GeForce RTX 4070 → ~1,957.5 yes 142k ~$599
Intel Arc Pro B70 → ~1,954.3 yes 423k —
Intel Arc A770 16GB → ~1,800 yes 198k ~$329
AMD Radeon RX 6800 XT → ~1,760 yes 198k ~$649
AMD Radeon RX 6900 XT → ~1,760 yes 198k ~$999
NVIDIA GeForce RTX 3070 → ~1,740 yes 86k ~$499
NVIDIA GeForce RTX 5060 Ti 16GB → ~1,740 yes 198k ~$429
NVIDIA GeForce RTX 5060 Ti 8GB → ~1,740 yes 86k ~$379
Intel Arc Pro B60 → ~1,465.7 yes 311k —
Intel Arc B580 12GB → ~1,465.7 yes 142k ~$249
NVIDIA GeForce RTX 4060 Ti 8GB → ~1,118.6 yes 86k ~$399
NVIDIA GeForce RTX 4060 Ti 16GB → ~1,118.6 yes 198k ~$499
NVIDIA DGX Spark → ~1,060.3 yes 1732k ~$3,999
AMD Ryzen AI Max+ 395 → ~880 yes 1732k ~$1,999
Intel Arc Pro B50 → ~720 yes 198k —
NVIDIA GeForce RTX 2050 Mobile → ~435 yes 30k —

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

→ Zagreus 0.4B overview → All hardware

FAQ

What Consumer GPU hardware runs Zagreus 0.4B?▶

On GenAIList, 33 Consumer GPU options can run Zagreus 0.4B at Q4 — the fastest is the NVIDIA GeForce RTX 5090 at ~6,960 tok/s.

How fast is Zagreus 0.4B on Consumer GPU hardware?▶

Estimated generation speed ranges from ~435 to ~6,960 tok/s at Q4 (memory-bandwidth bound). Click any option for its full estimate and any measured numbers.