Qwen2.5 7B Instruct
Qwen · released Sep 16, 2024 · Qwen/Qwen2.5-7B-Instruct
- Type
- Open weightsApache License 2.0
- Params
- 7.6B
- Context
- 33K
about 25K words of context
Our take
Written Aug 3, 2026Qwen 2.5 is a compact downloadable text model with a permissive Apache licence and a 32,768-token request limit. It excels at following output formats cheaply, but struggles with graduate-level reasoning and broad knowledge questions.
Pick this for low-cost instruction-following where format compliance matters more than reasoning depth, or for Apache-licensed deployment without usage restrictions. Skip it if you need strong performance on PhD-level science questions, broad academic knowledge, or guaranteed fast throughput from the cheapest hosts.
The case for it
- Strong instruction-format adherence for its size class, scoring 72.8% on the format-compliance benchmark we track.
- Permissive Apache 2.0 licence allows commercial use, fine-tuning and redistribution.
- Lowest input price among tracked offers, at a fraction of the cost of the priciest host in its set.
The case against it
- Very weak on graduate-level reasoning, with near-random performance on PhD-level science questions.
- Modest broad knowledge coverage, scoring under 40% on the professional and academic knowledge test.
- No measured throughput on the cheapest providers; only two hosts have verified speed figures, and the faster one costs several times more per token.
How good is it?
IntelligencePuzzles, maths, exam questions
Qwen2.5 7B Instruct is not on Arena Text (overall), which is where the rating would come from, so there is no rating here. It is on GPQA Diamond, in 11th of 16 with 6.5.
CodingWriting and fixing code on its own
Nobody we watch has scored Qwen2.5 7B Instruct for this. We would take the rating from Arena Coding.
AgenticPlanning, calling tools, staying on task
Nobody we watch has scored Qwen2.5 7B Instruct for this. We would take the rating from Arena Agent (IPS).
WritingWe do not rate this
Nobody we watch has scored this model for writing. Two boards come close and neither tests writing: Arena Creative Writing asks people which of two replies they prefer, and LiveBench Language tests whether a model understood a passage.
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, which is why they get no rating.
Can you run it yourself?
- Fits in memory
- weights load entirely on the card
- Spills to system RAM
- some weights offload; much slower
- Too large
- will not load even with offload
- est
- size is calculated; the verdict could change by 10%
Comfortable fit
GeForce RTX 4090 · 24 GB
Room to spare. 16.6 GB spare means a 10% error in the size would not change the answer.
GeForce RTX 5090 · 32 GB
Room to spare. 24.6 GB spare means a 10% error in the size would not change the answer.
Apple M1 (8-core GPU) · 16 GB
Room to spare. 5.8 GB spare means a 10% error in the size would not change the answer.
Memory use by level
Against a 24 GB card.
All 3 sizes here are calculated, not measured. We hold no measured file for this model, so each size comes from the parameter count and every verdict above inherits that uncertainty.
Check against your own machine → · All 71 devices, with every size →
Or rent it from someone else
Cheapest of 4 live listings. Picked at the widest standard context we hold, within one quantisation slice, so the numbers beside it are a price one host actually charges.
- per 1M tokens
- $0.040 in / $0.10 out
- Context served
- 33K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| Novita AI | $0.070 / $0.070 | 32K | not measured | Unknown | Unknown | Unknown |
| OpenRouter | $0.040 / $0.10 | 33K | not measured | Unknown | Unknown | Unknown |
| Phala | $0.040 / $0.10 | 33K | 41 tok/s | No | No | Confirmed |
| Together AIfp8 | $0.30 / $0.30 | 33K | 84 tok/s | No | No | Confirmed |
Novita AI
Together AIAcross the 4 listings we hold: 2 say they do not train on prompts, 0 say they do and 2 do not say. 2 appear in the zero-retention registry we check; the rest are unknown to us rather than confirmed either way.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
- ✓
- Supported
- ✗
- Not supported
- Not published
- host gave no parameter list
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| Novita AI | |||
| OpenRouter | ✓ | ✓ | ✓ |
| Phala | ✓ | ✓ | ✓ |
| Together AIfp8 | ✗ | ✓ | ✓ |
Tool calling: 2 of 4 listings say yes, 1 says no, 1 publishes no parameter list. JSON output: 3 of 4 listings say yes, 1 publishes no parameter list. Strict schema: 3 of 4 listings say yes, 1 publishes no parameter list.
Models people weigh against Qwen2.5 7B Instruct
When we formed this view
Dates behind this page
Prices last checked 35h ago
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.
- 1 of 4 listings publish no parameter list, so what their API accepts is unknown to us.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 2 of 4 listings do not say whether they train on prompts.
- We hold no cached-input rate for any of its listings.
Licence and identifiers
What the licence allowsApache License 2.0, 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
Apache License 2.0
Fully permissive: commercial use, redistribution, and derivatives allowed. Requires attribution and a copy of the license. Includes an express patent grant.
Identifiers
- Hugging Face
- Qwen/Qwen2.5-7B-Instruct
- Architecture
- Dense
- Modality record
- text->text
- Catalogue slug
- qwen-qwen2-5-7b-instruct