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

Qwen3 30B-A3B on RTX 3090

Yes — Qwen3 30B-A3B runs on the RTX 3090 (24 GB). Fastest community-measured generation speed: 153.6 tokens/s.

✓ runsllmactive30 series24GB VRAM
step-by-step recipe for this pair

Qwen3-30B-A3B on RTX 3090: Full-GPU MoE Chat at 153 tok/s

llmintermediate24GB+
model
name
Qwen3 30B-A3B
slug
qwen3-30b-a3b
vertical
llm
status
active
repo
huggingface.co ↗
open detail ↗
gpu
name
RTX 3090
slug
rtx-3090
vram
24 GB
series
30
open detail ↗
§02·benchmarks
TaskQuantSpeedVRAMWorksConfidenceSourceVerified
llmQ4_K2988.6prefill tokens/s✓hardware-corner.net· web2026-05-15
llmQ4_K153.6tokens/s✓hardware-corner.net· web2026-05-15
§03·how it was measured
§04·more Qwen3 30B-A3B recipes
§05·common questions
Can you run Qwen3 30B-A3B on RTX 3090?

Yes — Qwen3 30B-A3B runs on the RTX 3090 (24 GB). Fastest community-measured generation speed: 153.6 tokens/s.

Which quantizations have been tested for Qwen3 30B-A3B on RTX 3090?

Q4_K — measured in community benchmarks.

How fast is Qwen3 30B-A3B on RTX 3090?

Up to 153.6 tokens/s (llm), the fastest community-measured generation speed.

Are there step-by-step instructions for Qwen3 30B-A3B on RTX 3090?

Yes — a step-by-step recipe documents Qwen3 30B-A3B on the RTX 3090, linked at the top of this page.