Qwen3.5 VRAM requirements
Memory needed to run Qwen3.5 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 |
|---|---|---|---|---|---|
| 0.8B | 2.7 | 2.5 | 2.4 | 2.3 | 2.2 |
| 4B | 6.1 | 5.3 | 4.8 | 4.3 | 3.8 |
| 9B | 11 | 9.4 | 8.3 | 7.1 | 6.0 |
| 13B | 15 | 13 | 11 | 9.4 | 7.8 |
| 122B · 10B active | 125 | 102 | 86 | 71 | 56 |
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 |
|---|---|---|---|---|---|
| 0.8B | 0.5 | 0.1 | 0.3 | 0.5 | 2.1 |
| 4B | 2.3 | 0.2 | 0.6 | 1.2 | 4.8 |
| 9B | 5.1 | 0.2 | 0.6 | 1.2 | 4.8 |
| 13B | 7.3 | 0.2 | 0.7 | 1.3 | 5.4 |
| 122B · 10B active | 69 | 0.4 | 1.5 | 3.0 | 12 |
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.
- 0.8Bneeds about 2.3 GB
Smallest: RTX 3060 Laptop 6GB (6 GB), RTX 4050 6GB (6 GB), CMP 170HX (8 GB), M1 8GB (8 GB), and 102 more.
- 4Bneeds about 4.3 GB
Smallest: RTX 3060 Laptop 6GB (6 GB), RTX 4050 6GB (6 GB), CMP 170HX (8 GB), M1 8GB (8 GB), and 102 more.
- 9Bneeds about 7.1 GB
Smallest: NVIDIA P102-100 (10 GB), RTX 2080 Ti (11 GB), D700 12GB (12 GB), Intel Arc B580 12GB (12 GB), and 93 more.
- 13Bneeds about 9.4 GB
Smallest: D700 12GB (12 GB), Intel Arc B580 12GB (12 GB), Intel Arc Pro B70 (12 GB), RTX 3060 12GB (12 GB), and 91 more.
- 122B · 10B activeneeds about 71 GB
Smallest: M2 Max 96GB (96 GB), M3 Max 96GB (96 GB), M3 Ultra 96GB (96 GB), M4 Max 96GB (96 GB), and 20 more.
Frequently asked
How much VRAM does Qwen3.5 need?
From about 2.3 GB for the 0.8B model to about 71 GB for the 122B · 10B 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 Qwen3.5 on a 16GB GPU?
Yes. The 13B model needs about 9.4 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 Qwen3.5 on a 24GB GPU such as an RTX 3090 or 4090?
Yes. The 13B model needs about 9.4 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.