// RUN ON CONSUMER GPU

Run ERNIE-4.5-0.3B 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 → ~7,733.3 yes 423k ~$1,999
NVIDIA GeForce RTX 4090 → ~4,350 yes 311k ~$1,599
NVIDIA GeForce RTX 3090 Ti → ~4,350 yes 311k ~$1,999
NVIDIA GeForce RTX 5080 → ~4,142.9 yes 199k ~$999
NVIDIA GeForce RTX 3090 → ~4,039.3 yes 311k ~$1,499
NVIDIA GeForce RTX 3080 Ti → ~3,935.7 yes 142k ~$1,199
NVIDIA GeForce RTX 5070 Ti → ~3,866.7 yes 199k ~$749
AMD Radeon RX 7900 XTX → ~3,666.7 yes 311k ~$999
NVIDIA GeForce RTX 3080 10GB → ~3,279.8 yes 114k ~$699
NVIDIA GeForce RTX 4080 → ~3,176.2 yes 199k ~$1,199
AMD Radeon RX 7900 XT → ~3,055.6 yes 255k ~$899
NVIDIA GeForce RTX 5070 → ~2,900 yes 142k ~$549
NVIDIA GeForce RTX 4070 Ti Super → ~2,900 yes 199k ~$799
NVIDIA GeForce RTX 3070 Ti → ~2,623.8 yes 86k ~$599
AMD Radeon RX 9070 XT → ~2,459.7 yes 199k ~$599
AMD Radeon RX 7800 XT → ~2,383.3 yes 199k ~$499
NVIDIA GeForce RTX 4070 Super → ~2,175 yes 142k ~$599
NVIDIA GeForce RTX 4070 → ~2,175 yes 142k ~$599
Intel Arc Pro B70 → ~2,171.4 yes 423k —
Intel Arc A770 16GB → ~2,000 yes 199k ~$329
AMD Radeon RX 6800 XT → ~1,955.6 yes 199k ~$649
AMD Radeon RX 6900 XT → ~1,955.6 yes 199k ~$999
NVIDIA GeForce RTX 3070 → ~1,933.3 yes 86k ~$499
NVIDIA GeForce RTX 5060 Ti 16GB → ~1,933.3 yes 199k ~$429
NVIDIA GeForce RTX 5060 Ti 8GB → ~1,933.3 yes 86k ~$379
Intel Arc Pro B60 → ~1,628.6 yes 311k —
Intel Arc B580 12GB → ~1,628.6 yes 142k ~$249
NVIDIA GeForce RTX 4060 Ti 8GB → ~1,242.9 yes 86k ~$399
NVIDIA GeForce RTX 4060 Ti 16GB → ~1,242.9 yes 199k ~$499
NVIDIA DGX Spark → ~1,178.1 yes 1732k ~$3,999
AMD Ryzen AI Max+ 395 → ~977.8 yes 1732k ~$1,999
Intel Arc Pro B50 → ~800 yes 199k —
NVIDIA GeForce RTX 2050 Mobile → ~483.3 yes 30k —

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

→ ERNIE-4.5-0.3B overview → All hardware

FAQ

What Consumer GPU hardware runs ERNIE-4.5-0.3B?▶

On GenAIList, 33 Consumer GPU options can run ERNIE-4.5-0.3B at Q4 — the fastest is the NVIDIA GeForce RTX 5090 at ~7,733.3 tok/s.

How fast is ERNIE-4.5-0.3B on Consumer GPU hardware?▶

Estimated generation speed ranges from ~483.3 to ~7,733.3 tok/s at Q4 (memory-bandwidth bound). Click any option for its full estimate and any measured numbers.