How much VRAM does Qwen 2.5 VL 72B need?

Qwen 2.5 VL 72B (72B parameters) requires approximately 70.4 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.

Can it run?

Yes, Gaudi 3 128GB can run Qwen 2.5 VL 72B with a C grade (Runs well). Expected decode speed: 60.7 tok/s.

CUsable

Runs well

Using Q4_K_M in vLLM

Capabilities:

Fit status

Runs well

Decode

60.7 tok/s

TTFT

3192 ms

Safe context

29K

Memory

70.4 GB / 128.0 GB

Weights43.9 GB

KV Cache11.3 GB

Runtime2.4 GB

Headroom12.8 GB

Workload	Grade	Fit	Decode	TTFT	Context
Agentic Coding	C	Runs well	59.0 tok/s	4775 ms	33K
Chat	C	Runs well	59.0 tok/s	1791 ms	16K
Coding	C	Runs well	60.7 tok/s	3192 ms	29K
RAG	C	Runs well	59.0 tok/s	5969 ms	33K
Reasoning	C	Runs well	59.0 tok/s	3880 ms	29K

How Qwen 2.5 VL 72B (72B params) fits at each quantization level on Gaudi 3 128GB (128.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	28.1 GB	Low	D34
Q3_K_S	3	35.3 GB	Low	D35
NVFP4	4

Ollama

ollama run qwen-2.5-vl-72b

HuggingFace

huggingface-cli download qwen-2.5-vl-72b

Upgrade options

NVIDIA H200 141GBBudget pick

C91.8 tok/s decode

~$30,000 MSRP

NVIDIA H200 PCIe 141GBBest value

C91.8 tok/s decode

~$30,000 MSRP