Qwen3 VRAM requirements
Memory needed to run Qwen3 at every published size and quant, with an 8k context. Each figure is weights plus KV cache plus runtime buffers, from the same memory model as the VRAM calculator.
Total memory by size and quant
GB at an 8k context. Bold is the Q4_K_M column, the usual starting point.
| Size | Q8_0 | Q6_K | Q5_K_M | Q4_K_M | Q3_K_M |
|---|---|---|---|---|---|
| 0.6B | 2.9 | 2.8 | 2.7 | 2.6 | 2.5 |
| 1.7B | 4.4 | 4.1 | 3.9 | 3.6 | 3.4 |
| 4B | 7.0 | 6.2 | 5.7 | 5.2 | 4.7 |
| 8B | 11 | 9.5 | 8.5 | 7.5 | 6.5 |
| 14B | 17 | 14 | 13 | 11 | 9.2 |
| 30B · 3B active | 34 | 28 | 25 | 21 | 17 |
| 30B · 3.3B active | 34 | 28 | 25 | 21 | 17 |
| 32B | 36 | 30 | 26 | 22 | 18 |
| 235B · 22B active | 239 | 195 | 165 | 136 | 107 |
KV cache by context length
GB the context alone adds on top of the weights. Add this to a weights figure to size a longer session.
| Size | Weights at Q4_K_M | 4k ctx | 16k ctx | 32k ctx | 128k ctx |
|---|---|---|---|---|---|
| 0.6B | 0.3 | 0.3 | 1.1 | 2.1 | 8.6 |
| 1.7B | 1.0 | 0.5 | 1.9 | 3.8 | 15 |
| 4B | 2.3 | 0.6 | 2.4 | 4.8 | 19 |
| 8B | 4.5 | 0.6 | 2.4 | 4.8 | 19 |
| 14B | 7.9 | 0.7 | 2.7 | 5.4 | 21 |
| 30B · 3B active | 17 | 1.1 | 4.3 | 8.6 | 34 |
| 30B · 3.3B active | 17 | 1.1 | 4.3 | 8.6 | 34 |
| 32B | 18 | 1.1 | 4.3 | 8.6 | 34 |
| 235B · 22B active | 132 | 1.1 | 4.3 | 8.6 | 34 |
What each size fits on at Q4_K_M
Hardware whose memory holds the model with headroom, smallest pool first. Fits means under 85% of the pool at an 8k context. A Mac's pool is what macOS lets the GPU use - two thirds of its memory up to 32 GB, three quarters from 36 GB - not the whole of it.
- 0.6Bneeds about 2.6 GB
Smallest: AMD FirePro D700 6GB (6 GB), NVIDIA RTX 3050 6GB (6 GB), NVIDIA RTX 3060 Laptop 6GB (6 GB), NVIDIA RTX 4050 6GB (6 GB), and 131 more.
On a Mac: 8 GB or more, with macOS's default GPU limit.
- 1.7Bneeds about 3.6 GB
Smallest: AMD FirePro D700 6GB (6 GB), NVIDIA RTX 3050 6GB (6 GB), NVIDIA RTX 3060 Laptop 6GB (6 GB), NVIDIA RTX 4050 6GB (6 GB), and 131 more.
On a Mac: 8 GB or more, with macOS's default GPU limit.
- 4Bneeds about 5.2 GB
Smallest: AMD Radeon Pro W6600 (8 GB), AMD RX 480 8GB (8 GB), AMD RX 5700 XT 8GB (8 GB), AMD RX 6600 (8 GB), and 127 more.
On a Mac: 16 GB or more, with macOS's default GPU limit.
- 8Bneeds about 7.5 GB
Smallest: AMD RX 6700 (10 GB), NVIDIA P102-100 (10 GB), NVIDIA RTX 3080 10GB (10 GB), NVIDIA GTX 1080 Ti (11 GB), and 106 more.
On a Mac: 16 GB or more, with macOS's default GPU limit.
- 14Bneeds about 11 GB
Smallest: AMD MI50 16GB (16 GB), AMD RX 6800 16GB (16 GB), AMD RX 6800 XT 16GB (16 GB), AMD RX 6900 XT 16GB (16 GB), and 87 more.
On a Mac: 24 GB or more, with macOS's default GPU limit.
- 30B · 3B activeneeds about 21 GB
Smallest: AMD MI50 32GB (32 GB), AMD Radeon AI PRO R9700 32GB (32 GB), AMD Radeon Pro V620 32GB (32 GB), AMD Radeon Pro W6800 (32 GB), and 41 more.
On a Mac: 36 GB or more, with macOS's default GPU limit.
- 30B · 3.3B activeneeds about 21 GB
Smallest: AMD MI50 32GB (32 GB), AMD Radeon AI PRO R9700 32GB (32 GB), AMD Radeon Pro V620 32GB (32 GB), AMD Radeon Pro W6800 (32 GB), and 41 more.
On a Mac: 36 GB or more, with macOS's default GPU limit.
- 32Bneeds about 22 GB
Smallest: AMD MI50 32GB (32 GB), AMD Radeon AI PRO R9700 32GB (32 GB), AMD Radeon Pro V620 32GB (32 GB), AMD Radeon Pro W6800 (32 GB), and 41 more.
On a Mac: 36 GB or more, with macOS's default GPU limit.
- 235B · 22B activeneeds about 136 GB
Smallest: NVIDIA B200 180GB (180 GB), AMD Gorgon Halo 192GB (192 GB), AMD Instinct MI300X 192GB (192 GB), NVIDIA B100 192GB (192 GB), and 3 more.
On a Mac: 256 GB or more, with macOS's default GPU limit.
Frequently asked
How much VRAM does Qwen3 need?
From about 2.6 GB for the 0.6B model to about 136 GB for the 235B · 22B active model, at Q4_K_M with an 8k context and including the KV cache and runtime buffers. Q8 needs more and Q3 less; the table above lists every size and rung.
Can I run Qwen3 on a 16GB GPU?
Yes. The 14B model needs about 11 GB at Q4_K_M with an 8k context, which fits a 16 GB card with headroom. Larger sizes need a smaller quant or a bigger card.
Can I run Qwen3 on a 24GB GPU such as an RTX 3090 or 4090?
Yes. The 14B model needs about 11 GB at Q4_K_M with an 8k context, which fits a 24 GB card with headroom. Larger sizes need a smaller quant or more memory.
How are these numbers calculated?
Weights at the quant's bits per weight, plus a KV cache sized from the model's attention design for the chosen context, plus compute buffers and a fixed runtime allowance. It is the same memory model the VRAM calculator uses. A family whose attention profile is not on file is sized as plain grouped-query attention, which errs towards needing more memory.