Qwen2.5 72B Instruct
Qwen · released Sep 16, 2024 · Qwen/Qwen2.5-72B-Instruct
- Type
- Open weightsCustom licence
- Params
- 72.7B
- Context
- 33K
about 25K words of context · download allowed, licence restricts use
Our take
Written Sep 4, 2026Qwen 2.5 is a large downloadable text model released in September 2024 with broad Arena coverage across seven categories. Its instruction-following accuracy is solid, though its knowledge and graduate-level reasoning scores are thin for the parameter count.
Pick this for general text tasks where a large open-weights model is preferred, or for instruction-following workflows at 84.8% measured accuracy. It suits budget-conscious hosting where the cheapest tracked tier is competitive. Skip it if you need multimodal input, a permissive licence, or strong graduate-level science reasoning.
The case for it
- Broadly measured across Arena categories, with scores spanning creative writing to coding.
- Strong instruction-following accuracy at 84.8% on IFEval.
- Arena coding score 52.8 points above its overall text score, suggesting relative strength there.
The case against it
- Weak on graduate-level science reasoning: 14.5% on GPQA Diamond.
- Thin broad knowledge for its size: 51.3% on MMLU-Pro.
- Custom licence with restrictions, not as permissive as Apache or MIT alternatives.
How good is it?
An open-weights text model for chat and general instruction following, though it trails most models on everyday questions, writing and coding.
- getting answers to everyday questionsArena Text (overall) · 148th of 168
- drafts, rewrites and editingArena Creative Writing · 149th of 168
- writing and completing codeArena Coding · 141st of 168
EverydayGeneral questions and everyday reasoning
Arena Text (overall)148th of 168 · 1303
CodingWriting and fixing code on its own
Arena Coding141st of 168 · 1355
Arena Coding is the only board that has scored it for this.
AgenticPlanning, calling tools, staying on task
Not yet scored on Arena Agent.
WritingDrafting and rewriting prose
Arena Creative Writing149th of 168 · 1254
Arena Creative Writing is the only board that has scored it for this.
These tests check whether a model follows instructions — a precondition for all the work above, but not a measure of how well that work is done.
Every published score for this model9 scoresEvery figure we hold, from 9 boards, with who ran it and a link to the source — including the boards no rating above is built on.
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. 22.9 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 4 hours ago — each listing carries its own date.
- per 1M tokens
- $0.36 in / $0.40 out
- Context served
- 33K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouterOpenRouter's own listing | $0.36 / $0.40checked 4 hours ago | 33K | not measured | Unknown | Unknown | Unknown |
| DeepInfrafp8Direct and through OpenRouter | $0.36 / $0.40checked 4 hours ago | 33K16K max reply through OpenRouter | 20 tok/sthrough OpenRouter | DirectUnknownThrough OpenRouterNo | DirectUnknownThrough OpenRouterNo | DirectUnknownThrough OpenRouterConfirmed |
| Novita AIbf16Direct and through OpenRouter | $0.38 / $0.40checked 4 hours ago | 32K8K max reply through OpenRouter | 17 tok/sthrough OpenRouter | DirectUnknownThrough OpenRouterNo | DirectUnknownThrough OpenRouterNo | DirectUnknownThrough OpenRouterConfirmed |
DeepInfra
Novita AIAcross the 3 listings we hold: 2 say they do not train on prompts (all of them only through OpenRouter), 0 say they do and 1 does not say. 2 appear in the zero-retention registry we check (all of them only through OpenRouter); 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 |
|---|---|---|---|
| OpenRouterOpenRouter's own listing | ✓ | ✓ | ✓ |
| DeepInfrafp8Direct and through OpenRouter | ✓ | ✓ | ✓ |
| Novita AIbf16Direct and through OpenRouter | ✓ | ✗ | ✗ |
Tool calling: 3 of 3 listings say yes. JSON output: 2 of 3 listings say yes, 1 says no. Strict schema: 2 of 3 listings say yes, 1 says no.
Models people weigh against Qwen2.5 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.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 1 of 3 listings does not say whether it trains on prompts, and 2 answer only through OpenRouter, not for their own listing.
- We hold no cached-input rate for any of its listings.
- 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/Qwen2.5-72B-Instruct
- Architecture
- Dense
- Takes in, gives back
- Text in, text out
- Catalogue slug
- qwen-qwen2-5-72b-instruct