VOOZH about

URL: https://willitrunai.com/can-run/qwen-3-vl-30b-a3b-on-l40s-48gb

⇱ Qwen3-VL 30B A3B Instruct on NVIDIA L40S 48GB? YES

Can Qwen3-VL 30B A3B Instruct run on NVIDIA L40S 48GB?

YES — Runs Great

S96Excellent
○Estimated from fit model

Qwen3-VL 30B A3B Instruct needs ~27.0 GB VRAM. NVIDIA L40S 48GB has 48.0 GB. With Q4_K_M quantization, expect ~80 tok/s.

Runtime: vLLMCapacity: RoomyBandwidth: HighStack: OptimizedBottleneck: Balanced
Share:

Operating mode

Choose the run profile you care about

Interactive favors responsiveness, while light API and scale-out lean harder on serving readiness. The fit stays the same, but the recommendation lens changes.

Current mode

Balanced

Balanced for general local use. Keeps the ranking neutral across personal and serving workflows.

Capabilities:

Select quantization to explore

Q4_K_M (Medium quality) — 27.0 GB, 80.1 tok/s, Runs well
27.0 GB required48.0 GB available
56% VRAM used

Fit status

Runs well

Decode

80.1 tok/s

TTFT

2417 ms

Safe context

246K

Memory

27.0 GB / 48.0 GB

Memory breakdown

Weights18.3 GB
KV Cache1.5 GB
Runtime2.4 GB
Headroom4.8 GB

See how fast it feels

See how fast it feelsQwen3-VL 30B A3B Instruct on NVIDIA L40S 48GB
1st promptCold start — includes initialization
>Solve: If a train travels at 60 mph for 2.5 hours, how far does it go?
Let me work through this step by step. Given information: - Speed = 60 mph (miles per hour) - Time = 2.5 hours Formula: Distance = Speed x Time Calculation: Distance = 60 mph x 2.5 h = 150 miles The train travels 150 miles. Double-check: at 60 mph the train covers 60 miles each hour. In half an hour it covers 30 miles. So in 2.5 hours: 60 + 60 + 30 = 150 miles. Confirmed.
2nd promptWarm — model ready, no init overhead
>What if the train stops for 20 minutes halfway?
The stop doesn't change the total distance covered while moving, but it affects total trip time. Breakdown: - First half: 1.25 hours at 60 mph = 75 miles - Stop: 20 minutes (no distance) - Second half: 1.25 hours at 60 mph = 75 miles Total distance: 150 miles (same) Total time: 2.5 h + 0.33 h = 2.83 hours Average speed: 150 / 2.83 = 53 mph The distance stays the same but average speed drops to 53 mph because of the stop.
Estimated: 80.1 tok/s decode · 2.4s TTFT (warm) · 200 tok/s prefill

What limits this setup

This setup is broadly balanced for this model.

No major red flags

This recommendation has enough memory headroom and acceptable estimated speed for the selected workload.

Best improvement path

Performance by workload

WorkloadGradeFitDecodeTTFTContext
ChatSRuns well80.1 tok/s1318 ms246K
CodingSRuns well80.1 tok/s2417 ms246K
Agentic CodingSRuns well80.1 tok/s3516 ms246K
ReasoningSRuns well80.1 tok/s2857 ms246K
RAGSRuns well80.1 tok/s4395 ms246K

Quantization options

How Qwen3-VL 30B A3B Instruct (30B params) fits at each quantization level on NVIDIA L40S 48GB (48.0 GB usable).

QuantBitsVRAMQualityFit
Q2_K
2
11.7 GB
LowS86
Q3_K_S
3
14.7 GB
LowS87
NVFP4
4
16.8 GB
MediumS87
Q4_K_M
4
18.3 GB
MediumS88
Q5_K_M
5
21.6 GB
HighS89
Q6_K
6
24.6 GB
HighS90
Q8_0Best for your GPU
8
32.1 GB
Very HighS90
F16
16
61.5 GB
MaximumF0

Get started

Copy-paste commands to run Qwen3-VL 30B A3B Instruct on your machine.

Run

lms load Qwen3-VL-30B-A3B-Instruct && lms server start

Your hardware

More models your NVIDIA L40S 48GB can run

ModelParamsGradeDecodeCapabilities
👁 Alibaba
Qwen3-Coder 30B A3B Instruct		30.5BS77.4 tok/s
👁 Alibaba
Qwen 3.6 35B A3B		35BS65.1 tok/s

Frequently asked questions

See all results for NVIDIA L40S 48GBSee all hardware for Qwen3-VL 30B A3B Instruct