Can the RTX 5080 Mobile run Qwen3.6 35B A3B?
Not fully, but it's usable. Qwen3.6 35B A3B needs about 22.8 GB at Q4_K_M and the RTX 5080 Mobile has 16 GB - yet as a mixture-of-experts model it reads only ~3B parameters per token, so you can keep attention on the GPU and the experts in system RAM (llama.cpp --n-cpu-moe) and still get interactive speeds with 32 GB+ of RAM.
Every quantization
Qwen3.6 35B A3B (36B, 3B active) on 16 GB
| Quant | Weights | Needs | Fit | Est. speed |
|---|---|---|---|---|
| Q4_K_M | 21 GB | 22.8 GB | Too big | - |
| 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 RTX 5080 Mobile's 896 GB/s bandwidth (Estimated from memory bandwidth (llama.cpp decode)). Long contexts need more memory and run slower.
Run it with expert offload
Attention on the GPU, experts in system RAM
llama-server -hf unsloth/Qwen3.6-35B-A3B-GGUF -ngl 99 --n-cpu-moe 99Lower --n-cpu-moe step by step until the RTX 5080 Mobile's 16 GB is nearly full - each expert layer moved back to the GPU speeds things up. Needs about 16 GB+ of free system RAM.
What to do instead
Two ways forward
Cheapest cards that run it
- NVIDIA Tesla P40 - 24 GB, ~$159
- NVIDIA RTX 3090 - 24 GB, ~$750
- AMD Radeon RX 7900 XTX - 24 GB, ~$849
- NVIDIA RTX 3090 Ti - 24 GB, ~$899
Models that fit the RTX 5080 Mobile
- Qwen2.5-Coder-14B-Instruct - 14.8B, 9 GB at Q4
- Qwen3 14B - 14B, 8 GB at Q4
- Phi-4 - 14B, 8.5 GB at Q4
- Gemma 4 12B - 12B, 7 GB at Q4
Compare
Same model, other hardware - and other models on this card
Qwen3.6 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
- Radeon RX 7900 XTX~210 tok/s
- RTX 3090~209 tok/s
- MacBook Pro 16" M4 Max~119 tok/s
- Arc Pro B60~100 tok/s
Also runs on the RTX 5080 Mobile
- Qwen2.5-Coder-14B-Instruct~57 tok/s
- Qwen3 14B~64 tok/s
- Phi-4~60 tok/s
- Gemma 4 12B~73 tok/s
- Qwen3.5 9B~86 tok/s
- Llama 3.1 8B~93 tok/s
- Mistral-7B-Instruct-v0.2~129 tok/s
- Qwen3.5 4B~171 tok/s
Frequently asked
Quick answers
Can the GeForce RTX 5080 Mobile run Qwen3.6 35B A3B?
Not fully, but it's usable. Qwen3.6 35B A3B needs about 22.8 GB at Q4_K_M and the RTX 5080 Mobile has 16 GB - yet as a mixture-of-experts model it reads only ~3B parameters per token, so you can keep attention on the GPU and the experts in system RAM (llama.cpp --n-cpu-moe) and still get interactive speeds with 32 GB+ of RAM.
How much VRAM does Qwen3.6 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 Qwen3.6 35B A3B on the RTX 5080 Mobile?
It doesn't fit in the RTX 5080 Mobile's memory, so speed depends on how many layers you offload to system RAM - typically single-digit tokens per second or lower.