QwenReleased on Sep 19, 2024

Qwen2.5 7B Instruct: Benchmarks, Pricing & Size

Qwen2.5 7B Instruct is a language model from Qwen, released in September 2024.

Qwen2.5-7B-Instruct is an instruction-tuned 7B parameter language model that excels at following instructions, generating long texts (over 8K tokens), understanding structured data, and generating structured outputs like JSON. The model

Input
Text
Output
Text
Speed
Latency p95500ms
Throughput P95138char/s
Cost
$0.30/ 1M · 8:1 in:out
$0.30 in · $0.30 out

Qwen2.5 7B Instruct pricing

Providers

Qwen2.5 7B Instruct starts at $0.300 per million input tokens and $0.300 per million output tokens via Together.

ProviderInput $/MOutput $/MMax InputMax OutputLatency p95 sThroughput P95QuantInputOutput
Together logoTogether
$0.300$0.300131.1K8.2K
0.50
138 c/s
—

Qwen2.5 7B Instruct model size

Qwen2.5 7B Instruct has 7.6 billion parameters and was trained on 18 trillion tokens. See how it compares to other models in the same parameter range.

ParametersTraining tokens
7.6B
18Ttokens
2365× tokens-to-params ratio
Small (3–10B)
7.6B
1B7B70B405B

Qwen2.5 7B Instruct API

API access coming soon

Qwen2.5 7B Instruct will be available through our gateway shortly.

Qwen2.5 7B Instruct examples

Recent arena outputs from Qwen2.5 7B Instruct, picked from the highest-ranked matchups.

Qwen2.5 7B Instruct license

Qwen2.5 7B Instruct is released under the Apache 2.0 license, which permits commercial use, has 7.6B parameters.

License
Apache 2.0
Commercial use allowed
Parameters
7.6B

Apache License 2.0 - allows commercial use

FAQ

Common questions about Qwen2.5 7B Instruct.

When was Qwen2.5 7B Instruct released?

Qwen2.5 7B Instruct was released on September 19, 2024 by Qwen. This is the official Qwen2.5 7B Instruct release date tracked on LLM Stats.

Is Qwen2.5 7B Instruct available via API?

Yes, Qwen2.5 7B Instruct is available via API. See the official documentation for authentication and endpoint details. It is served by 1 provider tracked on LLM Stats.

How big is Qwen2.5 7B Instruct?

Qwen2.5 7B Instruct has 7.6 billion parameters. It was trained on 18.0 trillion tokens. It ships as an open-weight model, so you can download and run it on your own hardware.

Who created Qwen2.5 7B Instruct?

Qwen2.5 7B Instruct was created by Qwen.

What is the license for Qwen2.5 7B Instruct?

Qwen2.5 7B Instruct is released under the Apache 2.0 license. This is an open-source / open-weight license that permits self-hosting.

Where can I use Qwen2.5 7B Instruct?

Qwen2.5 7B Instruct is available through 1 provider including Together.

Where is the Qwen2.5 7B Instruct paper or technical report?

Qwen2.5 7B Instruct has a paper or technical report available at https://arxiv.org/abs/2407.10671. Use that source for architecture, training, release and evaluation details.