Qwen3-4B-Instruct-2507
An updated 4B-parameter non-thinking causal language model from Qwen, with significant improvements in instruction following, logical reasoning, text comprehension, mathematics, science, coding and tool usage.
text → text · made by Alibaba
Sold by 3 ways
| Seller | Lane | Rate |
|---|---|---|
| Hugging Face Inference Providers aggregator | nscale | $0.01per Mtok in$0.03per Mtok outrouter.huggingface.co · read 2026-08-25 |
| Fireworks AI aggregator | standard | $0.2per Mtok in$0.2per Mtok outraw.githubusercontent.com · read 2026-11-01 |
| Featherless AI aggregator | standard | $0.4per Mtok in$0.8per Mtok outapi.featherless.ai · read 2026-09-20 |
Measured 2 standings
| Place | Board | Metric | Score |
|---|---|---|---|
| 195thof 306 | OTIS Mock AIME 2024-2025 | mean_score | 52.222 |
| 265thof 326 | GPQA Diamond | mean_score | 45.833 |
About
Qwen3-4B-Instruct-2507 — a text model from Alibaba, sold by 3 companies from $0.2 in and $0.2 out per million tokens, placed 195th of 306 on OTIS Mock AIME 2024-2025.
It takes text and returns text, with a context window of 32,768 tokens. It was published in July 2025. Its sellers say it can reason step by step and call a tool. The catalogue files it under reasoning. Three companies sell it. The cheapest is $0.2 in and $0.2 out per million tokens at Fireworks AI. Beside the standard rate there is a separately routed lane. It has been measured on 2 boards, and stands best at 195th of 306 on OTIS Mock AIME 2024-2025.
Every current figure
- Maker
- Alibaba
- Register
- model
- Takes
- text
- Returns
- text
- Context
- 32,768 tokens
- Published
- July 2025
- Parameters
- 4 billion · read from its own name
- Licence
- not read
- Sellers
- 3
- Maker's own price
- not read
- Price
- $0.2 in and $0.2 out per million tokens — Fireworks AI
- Boards
- 2
- Best place
- 195th of 306 — OTIS Mock AIME 2024-2025
Known as 4 names
Qwen/Qwen3-4B-Instruct-2507dnotitia/Qwen3-4B-Instruct-2507oceanicity/Qwen3-4B-Instruct-2507unsloth/Qwen3-4B-Instruct-2507