// RUN ON CONSUMER GPU

Run DeepSeek-R1-Distill-Qwen-1.5B 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 → ~1,564 yes 411k ~$1,999
NVIDIA GeForce RTX 4090 → ~879.8 yes 299k ~$1,599
NVIDIA GeForce RTX 3090 Ti → ~879.8 yes 299k ~$1,999
NVIDIA GeForce RTX 5080 → ~837.9 yes 187k ~$999
NVIDIA GeForce RTX 3090 → ~816.9 yes 299k ~$1,499
NVIDIA GeForce RTX 3080 Ti → ~796 yes 130k ~$1,199
NVIDIA GeForce RTX 5070 Ti → ~782 yes 187k ~$749
AMD Radeon RX 7900 XTX → ~741.6 yes 299k ~$999
NVIDIA GeForce RTX 3080 10GB → ~663.3 yes 102k ~$699
NVIDIA GeForce RTX 4080 → ~642.4 yes 187k ~$1,199
AMD Radeon RX 7900 XT → ~618 yes 243k ~$899
NVIDIA GeForce RTX 5070 → ~586.5 yes 130k ~$549
NVIDIA GeForce RTX 4070 Ti Super → ~586.5 yes 187k ~$799
NVIDIA GeForce RTX 3070 Ti → ~530.7 yes 74k ~$599
AMD Radeon RX 9070 XT → ~497.5 yes 187k ~$599
AMD Radeon RX 7800 XT → ~482 yes 187k ~$499
NVIDIA GeForce RTX 4070 Super → ~439.9 yes 130k ~$599
NVIDIA GeForce RTX 4070 → ~439.9 yes 130k ~$599
Intel Arc Pro B70 → ~439.2 yes 411k —
Intel Arc A770 16GB → ~404.5 yes 187k ~$329
AMD Radeon RX 6800 XT → ~395.5 yes 187k ~$649
AMD Radeon RX 6900 XT → ~395.5 yes 187k ~$999
NVIDIA GeForce RTX 3070 → ~391 yes 74k ~$499
NVIDIA GeForce RTX 5060 Ti 16GB → ~391 yes 187k ~$429
NVIDIA GeForce RTX 5060 Ti 8GB → ~391 yes 74k ~$379
Intel Arc Pro B60 → ~329.4 yes 299k —
Intel Arc B580 12GB → ~329.4 yes 130k ~$249
NVIDIA GeForce RTX 4060 Ti 8GB → ~251.4 yes 74k ~$399
NVIDIA GeForce RTX 4060 Ti 16GB → ~251.4 yes 187k ~$499
NVIDIA DGX Spark → ~238.3 yes 1720k ~$3,999
AMD Ryzen AI Max+ 395 → ~197.8 yes 1720k ~$1,999
Intel Arc Pro B50 → ~161.8 yes 187k —
NVIDIA GeForce RTX 2050 Mobile → ~97.8 yes 18k —

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

→ DeepSeek-R1-Distill-Qwen-1.5B overview → All hardware

FAQ

What Consumer GPU hardware runs DeepSeek-R1-Distill-Qwen-1.5B?▶

On GenAIList, 33 Consumer GPU options can run DeepSeek-R1-Distill-Qwen-1.5B at Q4 — the fastest is the NVIDIA GeForce RTX 5090 at ~1,564 tok/s.

How fast is DeepSeek-R1-Distill-Qwen-1.5B on Consumer GPU hardware?▶

Estimated generation speed ranges from ~97.8 to ~1,564 tok/s at Q4 (memory-bandwidth bound). Click any option for its full estimate and any measured numbers.