Can Qwen 2.5 VL 72B run on RTX 6000 Ada 48GB?

BARELY — Tight on Memory

A78Great

Estimated from fit model

Qwen 2.5 VL 72B needs ~54.5 GB VRAM. RTX 6000 Ada 48GB has 48.0 GB. With Q4_K_M quantization, expect ~11 tok/s.

Runtime: llama.cppCapacity: OffloadBandwidth: HighStack: StandardBottleneck: Host offload

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) — 54.5 GB, 11.2 tok/s, Very compromised (needs ~5.2 GB host RAM)

54.5 GB required48.0 GB available

114% VRAM needed

6.5 GB over capacity — needs offload or smaller quantization

Fit status

Very compromised (needs ~5.2 GB host RAM)

Decode

11.2 tok/s

TTFT

17304 ms

Safe context

Memory

54.5 GB / 48.0 GB

Offload

10%

Memory breakdown

Weights43.9 GB

KV Cache4.9 GB

Runtime0.9 GB

Headroom4.8 GB

See how fast it feels

See how fast it feelsQwen 2.5 VL 72B on RTX 6000 Ada 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: 11.2 tok/s decode · 17.3s TTFT (warm) · 28 tok/s prefill

What limits this setup

It fits through host-memory offload, and offload is the main reason performance drops.

CPU or host-memory offload is active

About 10% of the working set spills out of accelerator memory, which usually hurts latency and sustained decode throughput.

Very little memory headroom

You can run the model, but there is not much room left for longer context, bigger batches, extra apps, or future model updates.

Best improvement path

Remove offload with more accelerator memory

Prioritize a GPU or unified-memory tier that fits the whole model natively. Removing offload usually helps more than small compute gains.

Buy headroom, not only minimum fit

A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.

Increase host RAM if you keep offloading

This setup may need roughly 5.2 GB of extra host RAM just for the offloaded portion, before OS and other tools.

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	A	Very compromised (needs ~3.4 GB host RAM)	12.3 tok/s	8570 ms	4K
Coding	A	Very compromised (needs ~5.2 GB host RAM)	11.2 tok/s	17304 ms	4K
Agentic Coding	F	Too heavy	9.3 tok/s	30151 ms	4K
Reasoning	A	Very compromised (needs ~5.2 GB host RAM)	11.2 tok/s	20450 ms	4K
RAG	F	Too heavy	9.3 tok/s	37689 ms	4K

Quantization options

How Qwen 2.5 VL 72B (72B params) fits at each quantization level on RTX 6000 Ada 48GB (48.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	28.1 GB	Low	S88
Q3_K_SBest for your GPU	3	35.3 GB	Low	S88
NVFP4	4	40.3 GB	Medium	F0
Q4_K_M	4	43.9 GB	Medium	F0
Q5_K_M	5	51.8 GB	High	F0
Q6_K	6	59.0 GB	High	F0
Q8_0	8	77.0 GB	Very High	F0
F16	16	147.6 GB	Maximum	F0

Get started

Copy-paste commands to run Qwen 2.5 VL 72B on your machine.

Run

lms load Qwen2.5-VL-72B-Instruct && lms server start

Frequently asked questions

Can RTX 6000 Ada 48GB run Qwen 2.5 VL 72B?

Yes, RTX 6000 Ada 48GB can run Qwen 2.5 VL 72B with a A grade (Very compromised (needs ~5.2 GB host RAM)). Expected decode speed: 11.2 tok/s.

How much VRAM does Qwen 2.5 VL 72B need?

Qwen 2.5 VL 72B (72B parameters) requires approximately 54.5 GB of memory with Q4_K_M quantization.

What is the best quantization for Qwen 2.5 VL 72B?

The recommended quantization for Qwen 2.5 VL 72B is Q4_K_M, which balances quality and memory efficiency.

What speed will Qwen 2.5 VL 72B run at on RTX 6000 Ada 48GB?

On RTX 6000 Ada 48GB, Qwen 2.5 VL 72B achieves approximately 11.2 tokens per second decode speed with a time-to-first-token of 17304ms using Q4_K_M quantization.

Can RTX 6000 Ada 48GB run Qwen 2.5 VL 72B for coding?

For coding workloads, Qwen 2.5 VL 72B on RTX 6000 Ada 48GB receives a A grade with 11.2 tok/s and 4K context.

What context window can Qwen 2.5 VL 72B use on RTX 6000 Ada 48GB?

On RTX 6000 Ada 48GB, Qwen 2.5 VL 72B can safely use up to 4K tokens of context. The model's official context limit is 33K, but available memory constrains the safe maximum.

What should I upgrade first if Qwen 2.5 VL 72B feels slow on RTX 6000 Ada 48GB?

Remove offload with more accelerator memory. Prioritize a GPU or unified-memory tier that fits the whole model natively. Removing offload usually helps more than small compute gains.

See all results for RTX 6000 Ada 48GB See all hardware for Qwen 2.5 VL 72B

Embed this result▼

Paste this snippet into any page to show a live fit card.

<iframe src="https://willitrunai.com/embed/qwen-2.5-vl-72b-on-rtx-6000-ada-48gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: