Alibaba Qwen
Can the Arc Pro B60 run Qwen3.5 35B-A3B (MoE)?
We earn from qualifying purchases via affiliate links. Disclosure.
Yes, but it's tight. Qwen3.5 35B-A3B (MoE) is a 22 GB download (Q4_K_M). The Arc Pro B60 gives the GPU 24 GB, leaving about 2 GB, so keep the context short (our estimate).
Does it fit?
| Qwen3.5 35B-A3B (MoE) memory | 22 GB at Q4_K_M (Ollama: qwen3.5 tags) |
|---|---|
| Arc Pro B60 GPU memory | 24 GB of VRAM (product listing). |
| Left over | About 2 GB (our arithmetic) |
| Verdict | Tight Under 4 GB to spare (our estimate bands) |
Recommended quantization and context
Use the Q4_K_M build that Ollama's tag downloads; the memory figure above is for that build. The model supports up to 256K of context, but longer context uses more memory. Ollama starts at a 4096-token context by default (Ollama FAQ).
With only about 2 GB spare, keep the default context. If ollama ps shows part of the model on the CPU, shorten the context or pick a smaller model.
Run it
ollama run qwen3.5:35b-a3bThen check it's on the GPU:
ollama psThe PROCESSOR column should read 100% GPU. Driver setup for Intel cards on Windows, Linux and macOS, plus common fixes, is in the install and run section.
Where to buy the Arc Pro B60
ASRock Intel Arc Pro B60 Creator 24GB
Price shown at Amazon
Sold at Amazon.
Check price at Amazon (opens in a new tab)FAQ
Can the Arc Pro B60 run Qwen3.5 35B-A3B (MoE)?
Yes, but tight: Qwen3.5 35B-A3B (MoE) needs 22 GB (Q4_K_M, Ollama library) and the Arc Pro B60 gives the GPU 24 GB, leaving about 2 GB. Keep the 4096-token default context. The fit bands are our estimate.
How much VRAM does Qwen3.5 35B-A3B (MoE) need?
22 GB for the Q4_K_M build in the Ollama library, plus roughly 1–4 GB for context and runtime (our estimate). See the 24 GB page for other models that fit.
What command runs Qwen3.5 35B-A3B (MoE)?
ollama run qwen3.5:35b-a3b. Then run "ollama ps" and check the PROCESSOR column reads 100% GPU.
How fast is Qwen3.5 35B-A3B (MoE) on the Arc Pro B60?
We don't list a speed because we have no sourced measurement for this pairing. Speed depends on memory bandwidth, quantization and context length.