Smaller Qwen coder for efficient local agents and repo-level fixes
https://api-inference.modelscope.cn/v1 Qwen/Qwen3-Coder-30B-A3B-Instruct | Benchmark | Score | Metric | Date |
|---|---|---|---|
| Artificial Analysis Coding Index | 19.4 | index | 2026-06-02 |
| SciCode | 27.8 | percent correct | 2026-06-02 |
| Terminal-Bench Hard | 15.2 | success rate | 2026-06-02 |
Qwen3-Coder-30B-A3B-Instruct is listed for chat workloads and supports a 8K context window.
Use it when ModelScope's free tier is enough for evaluation, demos, or light production traffic.
We found 2 provider listings for qwen3-coder-30b-a3b-instruct. Check model ID, quota, pricing, and API format before switching providers.
| Provider | Model listing | Access | Context | API | Limits |
|---|---|---|---|---|---|
| | Qwen/Qwen3-Coder-30B-A3B-Instruct | Free tier | 8K | Native | Varies |
| | Qwen3-Coder-30B-A3B-Instruct | Free tier | 262K | OpenAI-style | 2 RPM (anonymous) |
| Model | Provider | Context | Access |
|---|---|---|---|
| Qwen3-Coder-30B-A3B-Instruct | OVHcloud AI Endpoints | 262K | Free tier |
| Qwen/Qwen3.5-35B-A3B | ModelScope | 131K | Check provider |
| Qwen/Qwen3.5-27B | ModelScope | 131K | Check provider |
| MiniMax-M2.5-highspeed | ModelScope | 205K | Check provider |
| Kimi K2.5 | ModelScope | 262K | Check provider |
Qwen3-Coder-30B-A3B-Instruct is tagged for chat in this catalog and works with OpenAI-compatible client libraries.
Qwen3-Coder-30B-A3B-Instruct is listed with free API access on ModelScope, subject to the provider's quota and account policy.
The model ID shown in this catalog is Qwen/Qwen3-Coder-30B-A3B-Instruct.
The listed context window is 8K tokens with up to 4K output tokens.
Smaller Qwen coder for efficient local agents and repo-level fixes
For API keys, setup steps, and provider-level limits, see the ModelScope provider page.