self-hosted/ai
§01·compatibility · /check

Qwen3.5 35B on RTX 3090

Yes — Qwen3.5 35B runs on the RTX 3090 (24 GB). Fastest community-measured result: 2622.1 prefill tokens/s, with 24 GB peak VRAM.

runsmultimodalactive30 series24GB VRAM
step-by-step recipe for this pair

Qwen3.5-35B-A3B on RTX 3090: MXFP4 MoE Chat at 111 tok/s

multimodalintermediate24GB+
model
name
Qwen3.5 35B
slug
qwen3-5-35b
vertical
multimodal
status
active
open detail ↗
gpu
name
RTX 3090
slug
rtx-3090
vram
24 GB
series
30
open detail ↗
§02·benchmarks
TaskQuantSpeedVRAMWorksConfidenceSourceVerified
llmMXFP42622.1prefill tokens/s24GBhardware-corner.net· web2026-05-15
llmMXFP4111.2tokens/s24GBhardware-corner.net· web2026-05-15
§03·more Qwen3.5 35B recipes
§04·common questions
Can you run Qwen3.5 35B on RTX 3090?

Yes — Qwen3.5 35B runs on the RTX 3090 (24 GB). Fastest community-measured result: 2622.1 prefill tokens/s, with 24 GB peak VRAM.

How much VRAM does Qwen3.5 35B need on RTX 3090?

Measured peak VRAM is 24 GB.

Which quantizations have been tested for Qwen3.5 35B on RTX 3090?

MXFP4 — measured in community benchmarks.

How fast is Qwen3.5 35B on RTX 3090?

Up to 2622.1 prefill tokens/s (llm), the fastest community-measured result.

Are there step-by-step instructions for Qwen3.5 35B on RTX 3090?

Yes — a step-by-step recipe documents Qwen3.5 35B on the RTX 3090, linked at the top of this page.