// RUN ON CONSUMER GPU

Run Qwen3-1.7B 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 → ~1,637.6 yes 412k ~$1,999
NVIDIA GeForce RTX 4090 → ~921.2 yes 299k ~$1,599
NVIDIA GeForce RTX 3090 Ti → ~921.2 yes 299k ~$1,999
NVIDIA GeForce RTX 5080 → ~877.3 yes 187k ~$999
NVIDIA GeForce RTX 3090 → ~855.4 yes 299k ~$1,499
NVIDIA GeForce RTX 3080 Ti → ~833.4 yes 131k ~$1,199
NVIDIA GeForce RTX 5070 Ti → ~818.8 yes 187k ~$749
AMD Radeon RX 7900 XTX → ~776.5 yes 299k ~$999
NVIDIA GeForce RTX 3080 10GB → ~694.5 yes 103k ~$699
NVIDIA GeForce RTX 4080 → ~672.6 yes 187k ~$1,199
AMD Radeon RX 7900 XT → ~647.1 yes 243k ~$899
NVIDIA GeForce RTX 5070 → ~614.1 yes 131k ~$549
NVIDIA GeForce RTX 4070 Ti Super → ~614.1 yes 187k ~$799
NVIDIA GeForce RTX 3070 Ti → ~555.6 yes 75k ~$599
AMD Radeon RX 9070 XT → ~520.9 yes 187k ~$599
AMD Radeon RX 7800 XT → ~504.7 yes 187k ~$499
NVIDIA GeForce RTX 4070 Super → ~460.6 yes 131k ~$599
NVIDIA GeForce RTX 4070 → ~460.6 yes 131k ~$599
Intel Arc Pro B70 → ~459.8 yes 412k —
Intel Arc A770 16GB → ~423.5 yes 187k ~$329
AMD Radeon RX 6800 XT → ~414.1 yes 187k ~$649
AMD Radeon RX 6900 XT → ~414.1 yes 187k ~$999
NVIDIA GeForce RTX 3070 → ~409.4 yes 75k ~$499
NVIDIA GeForce RTX 5060 Ti 16GB → ~409.4 yes 187k ~$429
NVIDIA GeForce RTX 5060 Ti 8GB → ~409.4 yes 75k ~$379
Intel Arc Pro B60 → ~344.9 yes 299k —
Intel Arc B580 12GB → ~344.9 yes 131k ~$249
NVIDIA GeForce RTX 4060 Ti 8GB → ~263.2 yes 75k ~$399
NVIDIA GeForce RTX 4060 Ti 16GB → ~263.2 yes 187k ~$499
NVIDIA DGX Spark → ~249.5 yes 1720k ~$3,999
AMD Ryzen AI Max+ 395 → ~207.1 yes 1720k ~$1,999
Intel Arc Pro B50 → ~169.4 yes 187k —
NVIDIA GeForce RTX 2050 Mobile → ~102.4 yes 19k —

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

→ Qwen3-1.7B overview → All hardware

FAQ

What Consumer GPU hardware runs Qwen3-1.7B?▶

On GenAIList, 33 Consumer GPU options can run Qwen3-1.7B at Q4 — the fastest is the NVIDIA GeForce RTX 5090 at ~1,637.6 tok/s.

How fast is Qwen3-1.7B on Consumer GPU hardware?▶

Estimated generation speed ranges from ~102.4 to ~1,637.6 tok/s at Q4 (memory-bandwidth bound). Click any option for its full estimate and any measured numbers.