Can I Run Qwen 3.5 35B-A3B on NVIDIA GeForce RTX 5090?

Name: LLM Configurator — GPU VRAM Checker
Author: LLM Configurator

作者： Jakub Rusinowski · 最后更新： 2026年8月15日

Yes. Qwen 3.5 35B-A3B needs 21.1 GB at Q4_K_M and the NVIDIA GeForce RTX 5090 has 32 GB, leaving about 10.9 GB of headroom, at roughly 247 tok/s (estimated) with room for up to 32K of context.

The numbers

Model	Qwen 3.5 35B-A3B
Parameters	35B (3B active)
Quantization	Q4_K_M
VRAM needed	21.1 GB
NVIDIA GeForce RTX 5090 VRAM	32 GB
Verdict	Runs
Max context	32K
Estimated speed	~247 tok/s

What to do next

Nothing to change — run it at Q4_K_M. If you want more capability, check whether the next size up also fits.

联盟营销声明: 本页部分链接为联盟推广链接——如果你通过它们购买，LLM Configurator 可能会获得佣金，而你无需支付任何额外费用。作为亚马逊联盟成员（Amazon Associate），LLM Configurator 会从符合条件的购买中获得收益。

Running Qwen 3.5 35B-A3B on this card:

NVIDIA GeForce RTX 5090 32GB

32 GB VRAM · 575 W board power

2026年价格波动较大——请以当前商品页价格为准。

在亚马逊查看价格

Buy vs. rent Qwen 3.5 35B-A3B

Buy the GPU

~$1,999

NVIDIA GeForce RTX 5090 · MSRP

Rent by the hour

from $0.34/hr

RTX 4090 (24 GB) class

At 2 hrs/day, buying (~$1,999) beats renting at $0.34/hr after about 8.2 years.

Affiliate links — we may earn a commission if you sign up, at no extra cost to you.

RunPod $0.34/hr

Rent on RunPod →

Vast.ai $0.35/hr · typical low · varies

Rent on Vast.ai →

Cloud rates verified 2026-07 — estimates, and marketplace prices vary. Buying price is GPU MSRP only, not a full PC.

Other Qwen 3.5 sizes on the NVIDIA GeForce RTX 5090

Qwen 3.5 397B-A17B — does not fit (134.0 GB)
Qwen 3.5 122B-A10B — does not fit (73.7 GB)
Qwen 3.5 27B — runs (16.3 GB)
Qwen 3.5 9B — runs (5.4 GB)
Qwen 3.5 4B — runs (2.4 GB)
Qwen 3.5 2B — runs (1.2 GB)
Qwen 3.5 0.8B — runs (0.5 GB)

Qwen 3.5 35B-A3B on nearby hardware

Apple M2 (24 GB) — runs at a lower quant
Apple M3 Pro (36 GB) — runs

All Qwen 3.5 sizes on the NVIDIA GeForce RTX 5090 | VRAM calculator for Qwen 3.5 35B-A3B | NVIDIA GeForce RTX 5090 GPU page | Check your hardware