Can the Radeon RX 7900 XTX run Qwen3.5 35B A3B?
Just. Qwen3.5 35B A3B at Q4_K_M needs about 22.8 GB of the Radeon RX 7900 XTX's 24 GB, running at an estimated 210 tok/s. Keep context short and close other GPU apps.
Every quantization
Qwen3.5 35B A3B (36B, 3B active) on 24 GB
| Quant | Weights | Needs | Fit | Est. speed |
|---|---|---|---|---|
| Q4_K_M | 21 GB | 22.8 GB | Tight | ~210 tok/s |
| Q5_K_M | 26 GB | 27.8 GB | Too big | - |
| Q8_0 | 39 GB | 40.8 GB | Too big | - |
| FP16 | 72 GB | 73.8 GB | Too big | - |
Estimates. Needs = weights + 1.8 GB for KV cache and runtime at modest context. Speed is single-stream decode scaled from the Radeon RX 7900 XTX's 960 GB/s bandwidth (Estimated from memory bandwidth (llama.cpp decode)). Long contexts need more memory and run slower.
Run it
Copy, paste, go
llama-server -hf unsloth/Qwen3.5-35B-A3B-GGUF -ngl 99Ollama pulls a Q4 build by default. Pick a larger quant only if the table above says it fits. Full Qwen3.5 35B A3B details →
Compare
Same model, other hardware - and other models on this card
Qwen3.5 35B A3B on other hardware
- RTX 5090~391 tok/s
- RTX 5090 D~391 tok/s
- RTX 6000D~343 tok/s
- RTX 4090~238 tok/s
- RTX 3090~209 tok/s
- MacBook Pro 16" M4 Max~119 tok/s
- Arc Pro B60~100 tok/s
- DGX Spark (GB10)~60 tok/s
Also runs on the Radeon RX 7900 XTX
- GLM-4.7-Flash~212 tok/s
- Qwen3-30B-A3B-Instruct-2507~207 tok/s
- Qwen3.6 27B~34 tok/s
- Qwen3.8 27B~34 tok/s
- Gemma 4 26B A4B~162 tok/s
- gpt-oss-20b~183 tok/s
- Qwen2.5-Coder-14B-Instruct~61 tok/s
- Qwen3 14B~69 tok/s
Frequently asked
Quick answers
Can the AMD Radeon RX 7900 XTX run Qwen3.5 35B A3B?
Just. Qwen3.5 35B A3B at Q4_K_M needs about 22.8 GB of the Radeon RX 7900 XTX's 24 GB, running at an estimated 210 tok/s. Keep context short and close other GPU apps.
How much VRAM does Qwen3.5 35B A3B need?
About 21 GB of weights at Q4_K_M, 39 GB at Q8_0 and 72 GB at FP16. Add roughly 1.8 GB for the KV cache and runtime at modest context lengths.
How fast is Qwen3.5 35B A3B on the Radeon RX 7900 XTX?
Roughly 210 tokens per second at Q4_K_M (single user, llama.cpp-style decode). This is an estimate from the Radeon RX 7900 XTX's 960 GB/s memory bandwidth; as a mixture-of-experts model only about 3B parameters are read per token, which is why it is faster than its size suggests.