Qwen3.5 9B
Qwen3.5 9B needs 6.7 GB of VRAM at Q4_K_M with 8k context, computed from its config.json as checked on 3 November 2026. The smallest card that holds it has 8 GB, and the fastest desktop card that runs it, the RTX 5090, generates at most 223 tokens per second.
- Parameters
- 9.7B
- Context
- 262,144 tokens
- Licence
- Apache 2.0
- Released
- February 2026
- Config checked
- 3 November 2026
Open Qwen3.5 9B in the LLM checker
Which card size runs it
6.7 GB against each memory size. A model may use 95% of a card, and only what is left over, or missing, is coloured; tight means above 85%, with little room for a longer conversation.
Other quantisations, context lengths or a Q8 KV cache: the VRAM calculator.
Computed 3 November 2026Which GPU to pick
The smallest card here that loads it at Q4_K_M with 8k of context is the RTX 3060 (12 GB): 6.7 GB needed, an estimated 45 tokens per second. That is only the smallest card with its own page here: the model itself fits any 8 GB card. The same card still has room at 32,768 tokens of context (7.5 GB), so there is no reason to buy above it for this model.
At Q8_0, which is near-lossless, the card is the RTX 4060 Ti (16 GB), needing 11.5 GB. On Apple silicon, a Mac mini M4 Pro holds it with 32,768 tokens of context at an estimated 34 tokens per second; prompt processing is slower than on Nvidia, which long documents make obvious. Among unified-memory desktops, the Ryzen AI Max+ 395 holds it at 32,768 tokens in 7.5 GB, at an estimated 32 tokens per second.
Speed on each card
| GPU | Fits | Est. tokens/s | Feels like | Memory | Bandwidth |
|---|---|---|---|---|---|
| H100 SXM | Yes | ≤ 417 | faster than you can read | 80 GB | 3,350 GB/s |
| A100 | Yes | ≤ 254 | faster than you can read | 80 GB | 2,039 GB/s |
| RTX 5090 | Yes | ≤ 223 | faster than you can read | 32 GB | 1,792 GB/s |
| RTX PRO 6000 Blackwell | Yes | ≤ 223 | faster than you can read | 96 GB | 1,792 GB/s |
| RTX PRO 5000 Blackwell | Yes | ≤ 167 | faster than you can read | 48 GB | 1,344 GB/s |
| RTX 4090 | Yes | ≤ 125 | faster than you can read | 24 GB | 1,008 GB/s |
| RTX 5080 | Yes | ≤ 119 | faster than you can read | 16 GB | 960 GB/s |
| RX 7900 XTX | Yes | ≤ 119 | faster than you can read | 24 GB | 960 GB/s |
| RTX 6000 Ada | Yes | ≤ 119 | faster than you can read | 48 GB | 960 GB/s |
| RTX 3090 | Yes | ≤ 116 | faster than you can read | 24 GB | 936 GB/s |
| RTX 5070 Ti | Yes | ≤ 111 | faster than you can read | 16 GB | 896 GB/s |
| RTX 5090 Laptop GPU | Yes | ≤ 111 | faster than you can read | 24 GB | 896 GB/s |
| RTX PRO 4500 Blackwell | Yes | ≤ 111 | faster than you can read | 32 GB | 896 GB/s |
| L40S | Yes | ≤ 108 | faster than you can read | 48 GB | 864 GB/s |
| RX 7900 XT | Yes | 100 | faster than you can read | 20 GB | 800 GB/s |
| RTX A6000 | Yes | 96 | faster than you can read | 48 GB | 768 GB/s |
| RTX 4080 SUPER | Yes | 92 | faster than you can read | 16 GB | 736 GB/s |
| RTX 5070 | Yes | 84 | faster than you can read | 12 GB | 672 GB/s |
| RTX PRO 4000 Blackwell | Yes | 84 | faster than you can read | 24 GB | 672 GB/s |
| RX 9070 XT | Yes | 80 | faster than you can read | 16 GB | 640 GB/s |
| Radeon AI PRO R9700 | Yes | 80 | faster than you can read | 32 GB | 640 GB/s |
| Arc Pro B70 | Yes | 76 | faster than you can read | 32 GB | 608 GB/s |
| RTX 4070 | Yes | 63 | faster than you can read | 12 GB | 504 GB/s |
| Arc B580 | Yes | 57 | comfortable for chat | 12 GB | 456 GB/s |
| Arc Pro B60 | Yes | 57 | comfortable for chat | 24 GB | 456 GB/s |
| RTX 5060 Ti | Yes | 56 | comfortable for chat | 16 GB | 448 GB/s |
| RTX PRO 4000 Blackwell SFF | Yes | 54 | comfortable for chat | 24 GB | 432 GB/s |
| RTX 3060 | Yes | 45 | comfortable for chat | 12 GB | 360 GB/s |
| RX 9060 XT | Yes | 40 | comfortable for chat | 16 GB | 320 GB/s |
| RTX Spark | Yes | 37 | comfortable for chat | 128 GB (102 for the GPU) | 300 GB/s |
| RTX 4060 Ti | Yes | 36 | comfortable for chat | 16 GB | 288 GB/s |
| DGX Spark | Yes | 34 | comfortable for chat | 128 GB (126 for the GPU) | 273 GB/s |
| Ryzen AI Max+ 395 | Yes | 32 | comfortable for chat | 128 GB (96 for the GPU) | 256 GB/s |
Single-stream decode, from memory bandwidth at 70% efficiency. Prompt processing and batching not included. These are ceilings, not measurements: Qwen3.5 9B reads only 5.6 GB of weights per token at Q4, so little that the per-token costs the formula leaves out decide much of the real speed. The 14 figures marked ≤ are where a real runtime falls furthest below the number shown. See the speed estimator for other quantisations and Apple hardware, or every card compared if you are choosing hardware rather than a model.
Computed 3 November 2026Memory by quantisation and context
| Quant | 4,096 ctx | 8,192 ctx | 32,768 ctx |
|---|---|---|---|
| Q8_0 | 11.4 GB · fits 12 GB | 11.5 GB · fits 16 GB | 12.3 GB · fits 16 GB |
| Q5_K_M | 7.8 GB · fits 12 GB | 8 GB · fits 12 GB | 8.8 GB · fits 12 GB |
| Q4_K_M | 6.5 GB · fits 8 GB | 6.7 GB · fits 8 GB | 7.5 GB · fits 8 GB |
Weights at this quant: 5.6 GB at Q4. Every extra 1,000 tokens of context adds about 0.033 GB of KV cache at FP16, on top of a fixed 0.05 GB of recurrent state that does not grow. Try other settings in the VRAM calculator.
About the model
Qwen3.5 9B has 9.7B parameters. It has 32 layers, of which only 8 are full attention (4 KV heads of dimension 256) and keep a cache that grows with the conversation; the other 24 are Gated DeltaNet linear-attention layers with a small fixed state. The 9B model of Alibaba's Qwen3.5 family, February 2026, and one of the most downloaded open models of the year. Vision-language, 201 languages, hybrid attention.
Text, images and video 262,144-token window Apache 2.0 February 2026
The parameter count includes the vision encoder; a text-only GGUF is slightly smaller.
Native context window: 262,144 tokens. Licence: Apache 2.0, a permissive licence. Weights published in February 2026. It follows Qwen3 8B.
Good at
- The everyday model for an 8 to 12 GB card in 2026.
- Reading long files: a 262,144-token window whose cache stays small because only 8 of its 32 layers grow one.
- Image and document understanding without a second model.
Watch out for
- At Q8 it no longer fits a 12 GB card; the step up in precision costs a step up in hardware.
- The hybrid layers need a current runtime. On an old build the memory saving disappears.
Similar models
The models that need about the same memory as Qwen3.5 9B at Q4_K_M and 8k, which makes them the real alternatives on whatever card you have. The context column is what each extra 1,000 tokens costs, and it is where models of the same size differ most.
| Model | Size | Needs | Per 1k context | Window | Released |
|---|---|---|---|---|---|
| Qwen3.5 9B | 9.7B | 6.7 GB | 0.033 GB | 256k | 2026-02 |
| Qwen3 8B | 8.2B | 6.7 GB | 0.147 GB | 40k | 2025-04 |
| Llama 3.1 8B | 8B | 6.4 GB | 0.131 GB | 128k | 2024-07 |
| Granite 4.2 8B | 8.8B | 7.2 GB | 0.164 GB | 128k | 2026-08 |
| Gemma 4 12B | 12B | 8.2 GB | 0.016 GB | 256k | 2026-05 |
See every model compared, which models fit on 8 to 96 GB, or the cheapest hour of every cloud card.
Questions
- Can I run Qwen3.5 9B on a 24 GB card?
- Yes, at Q4_K_M and 8k context it needs about 6.7 GB, which fits a 24 GB card with room.
- How much VRAM does Qwen3.5 9B need at Q8?
- About 11.5 GB at 8k context, or 12.3 GB at 32k. Q8 is near-lossless; use it when it fits.
- What is the context length of Qwen3.5 9B?
- 262,144 tokens natively. Holding all of it at Q4_K_M takes about 15 GB, of which 8.6 GB is context.
- Why does Qwen3.5 9B need so little memory for long context?
- Because most of its layers do not keep a cache that grows. It has 32 layers, of which only 8 are full attention (4 KV heads of dimension 256) and keep a cache that grows with the conversation; the other 24 are Gated DeltaNet linear-attention layers with a small fixed state. At 32k tokens the context costs about 1.1 GB; if all 32 layers kept a conventional full-length cache, the same conversation would cost about 4.3 GB.
- How fast is Qwen3.5 9B on an RTX 4090?
- At most about 125 tokens per second at Q4, single stream, which is faster than you can read. That is a ceiling worked out from the card's memory bandwidth, not a measurement, and at a figure this high real runtimes land well below it, because the costs the formula leaves out take a growing share of each token.
- Architecture values from config.json in Qwen/Qwen3.5-9B on Hugging Face, checked 3 November 2026. Every figure on this page is computed from those values; check them before buying hardware for this model.
- Estimates assume a single conversation on a card that is otherwise free. A desktop on the same GPU takes 0.5 to 2 GB.