Qwen3 8B VRAM requirements
Qwen · 8.2B params · Apache 2.0. Estimates, not vendor numbers.
Qwen3 8B (8.2B parameters) needs about 6.4 GB of VRAM or unified memory at Q4, 7.3 GB at Q5 and 10 GB at Q8 (weights plus about 1.5 GB headroom, our estimate). The smallest common setup that runs it is 8GB GPU (RTX 4060).
| Quant | Download | Memory needed |
|---|---|---|
| Q4 | 4.9 GB | 6.4 GB |
| Q5 | 5.8 GB | 7.3 GB |
| Q8 | 8.7 GB | 10 GB |
Will it run on my machine?
| Setup | Runs? | Speed est. |
|---|---|---|
| 8GB GPU (RTX 4060) | Yes, Q4 | ~33 tok/s |
| 12GB GPU (RTX 3060 / 4070) | Yes, Q8 | ~35 tok/s |
| 16GB GPU (RTX 4060 Ti 16GB) | Yes, Q8 | ~20 tok/s |
| 24GB GPU (RTX 4090) | Yes, Q8 | ~69 tok/s |
| 32GB GPU (RTX 5090) | Yes, Q8 | ~123 tok/s |
| Mac 16GB (M4) | Yes, Q5 | ~12 tok/s |
| Mac 48GB (M4 Pro) | Yes, Q8 | ~19 tok/s |
| Mac 128GB (M4 Max) | Yes, Q8 | ~38 tok/s |
| PC, 32GB RAM, no GPU | Yes, Q4 | ~7 tok/s |
Best quant that fits each setup, with estimated generation speed from memory bandwidth. Real speed depends on the runtime, context length and settings.
Similar-size models
Phi-4 mini 3.8B (3.8B) · Qwen3 4B (4B) · Gemma 4 E4B (8B) · Ministral 3 8B (8B) · Llama 3.1 8B Instruct (8B) · Gemma 4 12B (11.95B)
FAQ
How much VRAM does Qwen3 8B need?
About 6.4 GB at Q4, 7.3 GB at Q5 and 10 GB at Q8, including about 1.5 GB headroom. These are estimates from the parameter count on the official model card.
Can Qwen3 8B run on 8GB of VRAM?
Yes, at Q4.
Can Qwen3 8B run on a Mac?
Yes. Mac 16GB (M4), Mac 48GB (M4 Pro), Mac 128GB (M4 Max) can run it.
Which quant of Qwen3 8B should I use?
Use the highest quant that fits with room to spare: Q8 is near full quality, Q5 is a good balance, and Q4 is the smallest that usually keeps quality acceptable.