Hardware guide · DeepSeek-R1-Distill
What hardware do you need to run DeepSeek-R1-0528-Qwen3-8B?
DeepSeek-R1-0528-Qwen3-8B needs about 6.2 GB to run at Q4_K_M, so the lightest hardware that runs it is iPhone 17 Pro. 33 of 40 devices tested can run it.
- Needs (Q4_K_M)
- ~6.2 GB
- Devices that run it
- 33
- Too small
- 7
- Lightest that runs it
- ~8 GB
Runs at Q4_K_M using ~6.2 GB of ~10.5 GB usable. You have room for Q8_0 for higher quality.
What kind of hardware runs DeepSeek-R1-0528-Qwen3-8B
Of the 33 devices that run it, here is the split by hardware class.
Hardware that runs DeepSeek-R1-0528-Qwen3-8B
Ranked by usable memory, lightest first. Prices are approximate street prices for the device itself (a GPU is the card alone; a Mac is the whole machine). Tok/s is a bandwidth estimate; see methodology.
- YesiPhone 17 Pro from $1,099~8 GB usable · uses ~6.2 GB · ~8 tok/s est.
- YesiPhone Air from $999~8 GB usable · uses ~6.2 GB · ~8 tok/s est.
- YesSamsung Galaxy S24 Ultra from $1,299~8.5 GB usable · uses ~6.2 GB · ~8 tok/s est.
- YesGeneric Android Phone (12GB RAM)~8.5 GB usable · uses ~6.2 GB
- YesApple M2 (16GB) from $1,199~10.5 GB usable · uses ~6.2 GB · ~17 tok/s est.
- YesApple M4 (16GB) from $999~10.5 GB usable · uses ~6.2 GB · ~21 tok/s est.
- YesGoogle Pixel 9 Pro from $999~10.5 GB usable · uses ~6.2 GB · ~7 tok/s est.
- YesApple M5 (16GB) from $1,099~10.5 GB usable · uses ~6.2 GB · ~26 tok/s est.
- YesGoogle Pixel 10 Pro from $999~10.5 GB usable · uses ~6.2 GB · ~7 tok/s est.
- YesNvidia GeForce RTX 3060 (12GB) from $329~11 GB usable · uses ~6.2 GB · ~50 tok/s est.
- YesNvidia GeForce RTX 4070 (12GB) from $599~11 GB usable · uses ~6.2 GB · ~70 tok/s est.
- YesApple M3 Pro (18GB) from $1,299~12 GB usable · uses ~6.2 GB · ~17 tok/s est.
- Yes16GB RAM Laptop (CPU/iGPU only) from $750~12 GB usable · uses ~6.2 GB · ~10 tok/s est.
- YesiPad Pro M4 (16GB, 1TB/2TB config) from $1,599~12 GB usable · uses ~6.2 GB · ~13 tok/s est.
- YesSamsung Galaxy S25 Ultra (16GB, 1TB config only) from $1,619~12 GB usable · uses ~6.2 GB · ~9 tok/s est.
- YesSamsung Galaxy S26 Ultra (16GB, 1TB config) from $1,299~12 GB usable · uses ~6.2 GB · ~9 tok/s est.
- YesNvidia GeForce RTX 4060 Ti (16GB) from $499~15 GB usable · uses ~6.2 GB · ~40 tok/s est.
- YesNvidia GeForce RTX 4080 (16GB) from $1,199~15 GB usable · uses ~6.2 GB · ~100 tok/s est.
- YesApple M4 (24GB) from $1,299~16 GB usable · uses ~6.2 GB · ~21 tok/s est.
- YesApple M4 Pro (24GB) from $1,999~16 GB usable · uses ~6.2 GB · ~47 tok/s est.
- YesApple M5 (32GB) from $1,299~21 GB usable · uses ~6.2 GB · ~26 tok/s est.
- YesNvidia GeForce RTX 4090 (24GB) from $1,599~23 GB usable · uses ~6.2 GB · ~140 tok/s est.
- YesNvidia GeForce RTX 3090 (24GB) from $1,499~23 GB usable · uses ~6.2 GB · ~130 tok/s est.
- YesAMD Radeon RX 7900 XTX (24GB) from $999~23 GB usable · uses ~6.2 GB · ~133 tok/s est.
- Yes32GB RAM Laptop (CPU/iGPU only) from $1,100~28 GB usable · uses ~6.2 GB · ~10 tok/s est.
- YesNvidia GeForce RTX 5090 (32GB) from $1,999~31 GB usable · uses ~6.2 GB · ~249 tok/s est.
- YesApple M4 Pro (48GB) from $2,399~32 GB usable · uses ~6.2 GB · ~47 tok/s est.
- YesApple M5 Pro (48GB) from $2,199~32 GB usable · uses ~6.2 GB · ~52 tok/s est.
- YesApple M4 Max (64GB) from $3,499~48 GB usable · uses ~6.2 GB · ~93 tok/s est.
- YesApple M4 Max (128GB) from $3,499~96 GB usable · uses ~6.2 GB · ~93 tok/s est.
- YesAMD Ryzen AI Halo (128GB) from $3,999~96 GB usable · uses ~6.2 GB · ~36 tok/s est.
- YesApple M5 Max (128GB) from $3,599~96 GB usable · uses ~6.2 GB · ~105 tok/s est.
- YesApple M3 Ultra (256GB) from $3,999~192 GB usable · uses ~6.2 GB · ~140 tok/s est.
Too small for DeepSeek-R1-0528-Qwen3-8B
See the full DeepSeek-R1-0528-Qwen3-8B memory breakdown, or compare it against other models.
Sources
Memory at Q4_K_M (6.2 GB = 4.68 GB weights + KV cache + overhead), validated 2026-08-03. See methodology.