Qwen3-Coder-30B-A3B-Instruct is an outstanding example of a high-quality large language model with advanced specialization in programming. This Mixture-of-Experts model has 30.5 billion total parameters, of which only 3.3 billion are activated per token, and out of 128 experts, only 8 are activated per token. The model comprises 48 hidden layers with grouped query attention (32 heads for Q and 4 for KV), delivering exceptional processing efficiency with minimal computational resource consumption. Native support for a 262,144-token context window—expandable up to 1 million tokens via Yarn—makes the model ideal for working with large code repositories within complex projects.
The key unique feature of Qwen3-Coder-30B-A3B-Instruct lies in its superior agent capabilities. The model does not merely generate code; it autonomously interacts with development tools, executes multi-step programming tasks, and is capable of solving complex problems without human intervention. On the LiveCodeBench v6 benchmark, the model achieves an impressive 66.0%, significantly outperforming the base version Qwen3-30B-A3B (57.4%). In AIME25 tasks (advanced mathematics for programming), it demonstrates 85.0% accuracy, surpassing Gemini-2.5-Flash-Thinking (72.0%) and confidently competing with much larger models. The model outperforms DeepSeek V3 on most coding tasks and delivers agent workflow performance comparable to Claude Sonnet 4, a remarkable achievement for an open-source solution.
Qwen3-Coder-30B-A3B-Instruct unlocks entirely new possibilities in software development. The model is integrated with popular agent-based programming platforms, including Qwen Code, CLINE, Roo Code, and Kilo Code, offering a unified function-calling format for seamless operation within CI/CD pipelines. Support for 358 programming languages makes it a universal reference tool for developers. The model particularly excels in repository-scale understanding scenarios, where it can analyze and modify massive codebases, automatically refactor legacy code, and create complex full-stack applications with minimal developer intervention.
| Model Name | Context | Type | GPU | Status | Link |
|---|
There are no public endpoints for this model yet.
An endpoint is a server with pre-installed software that automatically downloads neural network weights and launches an OpenAI-compatible API to handle incoming requests.
A private endpoint is created within the user's project, belongs exclusively to the user, and is billed per server configuration in accordance with the infrastructure pricing.
We recommend creating private endpoints when you need to:
| Name | GPU | TPS | Max Concurrency | |||
|---|---|---|---|---|---|---|
262,144.0 tensor |
4 | $1.26 | 1.199 | Launch | ||
262,144.0 pipeline |
3 | $1.34 | 1.631 | Launch | ||
262,144.0 tensor |
4 | $1.57 | 2.410 | Launch | ||
262,144.0 pipeline |
3 | $2.29 | 138.17 | 1.762 | Launch | |
262,144.0 |
1 | $2.37 | 281.00 | 2.274 | Launch | |
262,144.0 pipeline |
3 | $2.83 | 161.39 | 1.774 | Launch | |
262,144.0 tensor |
4 | $2.89 | 2.573 | Launch | ||
262,144.0 tensor |
2 | $2.93 | 1.531 | Launch | ||
262,144.0 tensor |
4 | $3.01 | 2.573 | Launch | ||
262,144.0 tensor |
4 | $3.60 | 2.567 | Launch | ||
262,144.0 |
1 | $3.83 | 179.56 | 2.246 | Launch | |
262,144.0 |
1 | $4.11 | 202.68 | 2.777 | Launch | |
262,144.0 tensor |
2 | $4.61 | 5.203 | Launch | ||
262,144.0 |
1 | $4.74 | 4.569 | Launch | ||
262,144.0 tensor |
2 | $9.40 | 9.845 | Launch | ||
| Name | GPU | TPS | Max Concurrency | |||
|---|---|---|---|---|---|---|
262,144.0 pipeline |
3 | $1.34 | 1.124 | Launch | ||
262,144.0 tensor |
4 | $1.62 | 1.903 | Launch | ||
262,144.0 pipeline |
6 | $1.65 | 1.644 | Launch | ||
262,144.0 pipeline |
3 | $2.29 | 154.00 | 1.261 | Launch | |
262,144.0 |
1 | $2.37 | 156.50 | 1.745 | Launch | |
262,144.0 pipeline |
3 | $2.83 | 148.67 | 1.239 | Launch | |
262,144.0 tensor |
4 | $2.89 | 2.065 | Launch | ||
262,144.0 tensor |
2 | $2.93 | 1.023 | Launch | ||
262,144.0 tensor |
4 | $3.01 | 2.065 | Launch | ||
262,144.0 tensor |
4 | $3.60 | 2.059 | Launch | ||
262,144.0 |
1 | $3.83 | 175.50 | 1.744 | Launch | |
262,144.0 |
1 | $4.11 | 196.88 | 2.276 | Launch | |
262,144.0 tensor |
2 | $4.61 | 4.695 | Launch | ||
262,144.0 |
1 | $4.74 | 4.062 | Launch | ||
262,144.0 tensor |
2 | $9.40 | 9.338 | Launch | ||
| Name | GPU | TPS | Max Concurrency | |||
|---|---|---|---|---|---|---|
262,144.0 |
1 | $4.11 | 196.26 | 1.113 | Launch | |
262,144.0 tensor |
2 | $4.61 | 142.52 | 3.564 | Launch | |
262,144.0 |
1 | $4.74 | 2.904 | Launch | ||
262,144.0 tensor |
2 | $4.93 | 142.52 | 3.564 | Launch | |
262,144.0 tensor |
4 | $5.74 | 2.103 | Launch | ||
262,144.0 pipeline |
6 | $5.83 | 2.540 | Launch | ||
262,144.0 tensor |
8 | $6.04 | 2.095 | Launch | ||
262,144.0 tensor |
8 | $7.51 | 2.089 | Launch | ||
262,144.0 tensor |
2 | $7.84 | 148.03 | 3.570 | Launch | |
262,144.0 tensor |
2 | $9.40 | 8.180 | Launch | ||
Contact our dedicated neural networks support team at support@immers.cloud or send your request to the sales department at sale@immers.cloud.