Qwen2.5-VL 72B VRAM Requirements

Qwen2.5-VL 72B at a glance

Made by

Alibaba, China

Released

January 27, 2025

Parameters

73.4B

Context window

125K tokens

License

Qwen license

Reads

Text, images and video

Knowledge cutoff

June 2024

OpenRouter

Papers

Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution (opens in a new tab) (2024)

Qwen-VL: A Frontier Large Vision-Language Model with Versatile Abilities (opens in a new tab) (2023)

Training

9.6 × 10²⁴ FLOP

Epoch AI (opens in a new tab), CC BY 4.0

On Hugging Face

666 likes, 101K downloads last month (opens in a new tab)

Runs with

vLLM, SGLang, llama.cpp (Ollama, LM Studio), MLX (Mac) · vLLM recipe (opens in a new tab)

Checked against

KV cache matches the GGUF header of bartowski/Qwen_Qwen2.5-VL-72B-Instruct-GGUF (opens in a new tab) (what llama.cpp allocates), November 6, 2026

On Ollama

ollama run qwen2.5vl:72b · Q4_K_M, 45.4 GiB 5.8M pulls (opens in a new tab)

VRAM by precision and context length

Weights plus the KV cache of one request (BF16 cache), in GiB. Add 1 to 3 GiB for the inference engine itself.

Qwen2.5-VL 72B GGUF files

Exact size of each quantization in bartowski/Qwen_Qwen2.5-VL-72B-Instruct-GGUF (opens in a new tab), and the smallest GPU that runs it with llama.cpp, Ollama or LM Studio and an 8K-token context.

Read every day from Hugging Face. Split files are added together; vision projectors are left out.

How many GPUs to run Qwen2.5-VL 72B

Fewest GPUs that fit the weights plus one 8K-token request. Data-center GPUs use vLLM (90% of memory usable), the others llama.cpp. Several GPUs split the model with tensor or pipeline parallelism.

8-bit: FP8 with vLLM (INT8 on GPUs without FP8), Q8_0 with llama.cpp. 4-bit: AWQ / GPTQ with vLLM, Q4_K_M with llama.cpp, both counted at the Q4_K_M size.

Cheapest way to run Qwen2.5-VL 72B today

For each GPU: the fewest cards that fit Qwen2.5-VL 72B with one 8K-token request, the most faithful weight format at that count, and the cheapest on-demand price (2026-11-06).

On-demand prices from AWS, Google Cloud, Azure, RunPod, Vast.ai, Oracle Cloud, OVHcloud, Scaleway, Verda, Akash and UpCloud, checked every hour. Serving many users needs more KV cache, so more memory: size it in the calculator. Some links are affiliate links: StudioTV may earn a commission, at no extra cost to you.

AWS, Google Cloud and UpCloud prices: Spare Cores (opens in a new tab), CC BY-SA 4.0 (opens in a new tab), shared under the same license.

Or use Qwen2.5-VL 72B through an API

No GPU to rent: these providers serve Qwen2.5-VL 72B and bill per token. Speeds are measured by Hugging Face for one request.

Prices and speeds from Hugging Face Inference Providers (opens in a new tab), read every day (November 6, 2026). An API wins at low volume; renting GPUs wins when they stay busy: the calculator gives the break-even.

Recommended settings for Qwen2.5-VL 72B

Sampling defaults from the official generation_config.json (opens in a new tab) of Qwen/Qwen2.5-VL-72B-Instruct.

vLLM and SGLang apply these defaults unless a request sets its own. With llama.cpp, pass them yourself: --temp 0 --repeat-penalty 1.05

KV cache: how memory grows with context

Architecture: 80 layers · 80 full attention (8 KV × 128). Every layer keeps keys and values for every token (grouped-query attention), so the cache grows linearly with context.

Qwen2.5-VL 72B VRAM badge

For a model card or a README: the 4-bit size and the smallest GPU it fits on, linked to this page. Data as JSON: /api/models/qwen2-5-vl-72b.json.

[![Qwen2.5-VL 72B VRAM](https://studiotvai.com/badge/qwen2-5-vl-72b.svg)](https://studiotvai.com/vram-requirements/qwen2-5-vl-72b)

Other models

Same family (dense): Llama 3.1 8B · Llama 3 8B · Llama 3.2 3B · Nanbeige4.3 33B · Granite 4.2 30B · Granite 4.2 8B · Granite 4.2 3B · MiniCPM5 2B · MiniCPM5 1B · Ministral 3 14B · Ministral 3 8B · Ministral 3 3B · Devstral 2 123B · Devstral Small 2 24B · Mistral Medium 3.5 128B · Magistral Small 1.2 24B · Mistral Small 3 24B · Mistral Large 2411 123B · Pixtral Large 124B · Codestral 22B · Mistral Small 2409 22B · Pixtral 12B · Nemotron 3.5 Parse · LLaVA 1.6 Mistral 7B · Mistral Small 3.2 24B · Qwen3 32B · Llama 3.3 70B · Llama 3.1 70B · Llama 3.1 405B · Youtu-Parsing-Omni · Mistral 7B v0.3 · Mistral Small 3.1 24B · Mistral Nemo · DeepSeek R1 Qwen3 8B · DeepSeek R1 Distill Qwen 32B · DeepSeek R1 Distill Qwen 14B · DeepSeek R1 Distill Qwen 7B · DeepSeek R1 Distill Llama 8B · Qwen3 4B · Qwen3 8B · Qwen2.5 7B · Qwen3 14B · Qwen2.5 3B · Qwen2.5 32B · Qwen2.5 14B · Qwen3-VL 8B · Qwen2.5-VL 7B · Qwen3-VL 4B · Qwen2.5-VL 3B · Qwen2.5-VL 32B · Qwen2-VL 7B · phi-4 · Phi-3.5-mini · Phi-4-mini · Phi-3-mini-128k · WeVisOne-VL 4B · Granite 4.1 3B · Mage-VL-Cowork · Qwen2 7B · Qwen2.5 72B · Qwen3-VL 32B · Qwen2.5 14B-1M

Estimates, not guarantees: computed from the official config.json with the same engine as the LLM VRAM Calculator. Real usage depends on your engine version and settings.