Skip to content

Can you run Qwen 3.5 35B-A3B on RTX 3080?

Short answer

Partly — Qwen 3.5 35B-A3B needs about 21.6 GB and RTX 3080 has 10 GB, so some layers run on the CPU.

Model file
20.5 GB
Needs in VRAM, with context
about 21.6 GB
Card memory
10 GB
Measured on this hardware
not measured

How this was worked out

Qwen 3.5 35B-A3B is a 20.5 GB file. Running it needs the weights in memory plus room for the context window and the runtime, which comes to roughly 21.6 GB in practice. RTX 3080 has 10 GB, which leaves -11.6 GB. That is arithmetic rather than a benchmark: it tells you whether the model loads, not how it feels.

What we have actually measured

We have not timed Qwen 3.5 35B-A3B on RTX 3080. The closest figure we have is no measurement of this model at all yet. Rather than scale that number to your card and present the result as a benchmark, this page leaves it out. The method is published at /benchmarks if you would like to run it yourself.

If it is tight

Nightjar will still load Qwen 3.5 35B-A3B on RTX 3080 by keeping some layers on the CPU, which works but costs speed. The next model down in the catalogue will fit entirely. Nightjar sizes the context window to the memory it finds, so a smaller card gets a shorter window rather than a failed load.

Smaller models that fit the same card

Related