Qwen2.5 VL 72B Instruct
Qwen · released Jan 27, 2025 · Qwen/Qwen2.5-VL-72B-Instruct
- Type
- Open weightsCustom licence
- Params
- 73.4B
- Context
- 128K
about 96K words of context · download allowed, licence restricts use
Our take
Written Sep 30, 2026Qwen2.5 VL 72B Instruct reads text and images together and returns written answers, and you can download it to run yourself. Its custom licence puts conditions on commercial use and redistribution, so read the terms before you build on it.
Use it for reading screenshots, diagrams or scanned pages alongside a written question, where you can judge the answers yourself, or when you want to run a vision model on your own hardware sized for 73.4 billion parameters. The licence puts conditions on commercial use and redistribution, so it needs reading before you build on it. Skip it if you need measured evidence of quality on vision or text tasks, which nothing here supplies.
The case for it
- Images go into the same request as the question, so a screenshot or diagram does not have to be described in words first.
- A long request can carry documents and images together, so they need not be split up first; reliable recall across all of it is unverified in our data.
The case against it
- The custom licence puts conditions on commercial use and redistribution, so it needs reading before you build on it.
- No benchmark scores are supplied, so vision and text ability need a trial on work you can check yourself.
- At 73.4 billion parameters this is a download for hardware sized to match, not a laptop model.
How good is it?
We hold no score for this model.
So there is no figure here for everyday use, coding, agent work or writing. That is a gap in our data, not a low score.
Can you run it yourself?
GeForce RTX 4090 · 24 GB
Too large for this card. The weights do not fit even with part of them offloaded to system memory.
Apple M1 Pro (16-core GPU) · 32 GB
Too large for this card. The weights do not fit even with part of them offloaded to system memory.
Comfortable fit
Apple M2 Max (38-core GPU) · 96 GB
Room to spare. 22.5 GB spare means a 10% error in the size would not change the answer.
Memory use by level
Against a 24 GB card.
What is quantisation? →This model on every device we track71 devicesThe Q4 build most people download, on each device: what the weights come to, how much context the memory leaves, and whether it runs. Smallest device that runs it first.
Check against your own machine → · Where to rent it hosted →
Or rent it from someone else
Prices checked between 4 hours and 21 days ago — each listing carries its own date.
The only listing at 128K of context — the other 2 in the table below are not like-for-like. One cheaper row there is outside that comparison: a different context length.
- per 1M tokens
- $0.80 in / $1.00 out
- Context served
- 128K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| Novita AIDirect | $0.80 / $0.80checked 21 days ago | 33K | not measured | Unknown | Unknown | Unknown |
| OpenRouterOpenRouter's own listing | $0.80 / $1.00checked 4 hours ago | 128K | not measured | Unknown | Unknown | Unknown |
| Parasailfp8Through OpenRouter | $0.80 / $1.00checked 4 hours ago | 128K115K max reply | 27 tok/s | No | No | Confirmed |
Novita AIAcross the 3 listings we hold: 1 says it does not train on prompts, 0 say they do and 2 do not say. 1 appears in the zero-retention registry we check; the rest are unknown to us.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| Novita AIDirect | |||
| OpenRouterOpenRouter's own listing | ✗ | ✓ | ✓ |
| Parasailfp8Through OpenRouter | ✗ | ✓ | ✓ |
Tool calling: 0 of 3 listings say yes, 2 say no, 1 publishes no parameter list. JSON output: 2 of 3 listings say yes, 1 publishes no parameter list. Strict schema: 2 of 3 listings say yes, 1 publishes no parameter list.
Models people weigh against Qwen2.5 VL 72B Instruct
When we formed this view
Recent changes
What moved
first indexed by our pipelineEach date is the day we first saw the change, or the day the maker announced it.
What we do not know about this model yet
- We hold no measured file for it, so all 3 sizes on this page are calculated from the parameter count.
- No independent board has scored it, so we hold no quality figures at all.
- 1 of 3 listings publishes no parameter list, so what its API accepts is unknown to us.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 2 of 3 listings do not say whether they train on prompts.
- We hold no batch or off-peak rate for any of its listings.
- We hold a decode speed for it, but no prompt-processing (prefill) figure, so how long the input side of a job takes is unknown to us.
Licence and identifiers
What the licence allowsCustom licence, what it allows commercially, and the identifiers you need to pull this model — its Hugging Face repo, our slug and a machine-readable card.
Licence
Custom licence
This model ships custom license terms that don't map to a known template. We haven't parsed them, so commercial use, redistribution and derivatives are unverified — review the original terms before shipping.
Identifiers
- Hugging Face
- Qwen/Qwen2.5-VL-72B-Instruct
- Architecture
- Dense
- Takes in, gives back
- Text and images in, text out
- Catalogue slug
- qwen-qwen2-5-vl-72b-instruct