Qwen3-Coder-30B-A3B-Instruct

coding

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.


Announce Date: 22.07.2025
Parameters: 31B
Experts: 128
Activated at inference: 4B
Context: 263K
Layers: 48
Attention Type: Full or Sliding Window Attention
Developer: Qwen
Transformers Version: 4.52.3
License: Apache 2.0

Public endpoint

Use our pre-built public endpoints for free to test inference and explore Qwen3-Coder-30B-A3B-Instruct capabilities. You can obtain an API access token on the token management page after registration and verification.
Model Name Context Type GPU Status Link
There are no public endpoints for this model yet.

Private server

Rent your own physically dedicated instance with hourly or long-term monthly billing.

We recommend deploying private instances in the following scenarios:

  • maximize endpoint performance,
  • enable full context for long sequences,
  • ensure top-tier security for data processing in an isolated, dedicated environment,
  • use custom weights, such as fine-tuned models or LoRA adapters.

Recommended server configurations for hosting Qwen3-Coder-30B-A3B-Instruct

Prices:
Name GPU Price, hour TPS Max Concurrency
teslat4-4.16.64.160
262,144.0
tensor
4 $0.96 1.164 Launch
teslaa2-4.32.128.160
262,144.0
tensor
4 $1.26 1.170 Launch
teslaa10-3.16.96.160
262,144.0
pipeline
3 $1.34 1.623 Launch
teslaa10-4.12.48.160
262,144.0
tensor
4 $1.57 2.381 Launch
rtx3090-3.16.96.160
262,144.0
pipeline
3 $2.29 1.745 Launch
rtxa5000-4.16.128.160.nvlink
262,144.0
tensor
4 $2.34 2.381 Launch
teslaa100-1.16.64.160
262,144.0
1 $2.37 137.990 2.281 Launch
rtx4090-3.16.96.160
262,144.0
pipeline
3 $2.83 1.740 Launch
rtx3090-4.16.64.160
262,144.0
tensor
4 $2.89 2.544 Launch
rtx5090-2.16.64.160
262,144.0
tensor
2 $2.93 1.543 Launch
rtx4090-4.16.64.160
262,144.0
tensor
4 $3.60 2.537 Launch
h100-1.16.64.160
262,144.0
1 $3.83 2.279 Launch
h100nvl-1.16.96.160
262,144.0
1 $4.11 2.812 Launch
teslaa100-2.24.96.160.nvlink
262,144.0
tensor
2 $4.61 5.215 Launch
h200-1.16.128.160
262,144.0
1 $4.74 4.603 Launch
h200-2.24.256.160.nvlink
262,144.0
tensor
2 $9.40 9.857 Launch
Prices:
Name GPU Price, hour TPS Max Concurrency
teslaa10-3.16.96.160
262,144.0
pipeline
3 $1.34 1.065 Launch
teslaa10-4.16.64.160
262,144.0
tensor
4 $1.62 1.824 Launch
teslaa2-6.32.128.160
262,144.0
pipeline
6 $1.65 1.015 Launch
rtx3090-3.16.96.160
262,144.0
pipeline
3 $2.29 1.187 Launch
rtxa5000-4.16.128.160.nvlink
262,144.0
tensor
4 $2.34 1.824 Launch
teslaa100-1.16.64.160
262,144.0
1 $2.37 127.020 1.724 Launch
rtx4090-3.16.96.160
262,144.0
pipeline
3 $2.83 1.183 Launch
rtx3090-4.16.64.160
262,144.0
tensor
4 $2.89 1.986 Launch
rtx4090-4.16.64.160
262,144.0
tensor
4 $3.60 1.980 Launch
h100-1.16.64.160
262,144.0
1 $3.83 1.721 Launch
h100nvl-1.16.96.160
262,144.0
1 $4.11 2.255 Launch
rtx5090-3.16.96.160
262,144.0
pipeline
3 $4.34 2.083 Launch
teslaa100-2.24.96.160.nvlink
262,144.0
tensor
2 $4.61 4.658 Launch
h200-1.16.128.160
262,144.0
1 $4.74 4.045 Launch
rtx5090-4.16.128.160
262,144.0
tensor
4 $5.74 3.181 Launch
h200-2.24.256.160.nvlink
262,144.0
tensor
2 $9.40 9.300 Launch
Prices:
Name GPU Price, hour TPS Max Concurrency
dedicated-rtx3090-8.64.128.960-1
262,144.0
tensor
8 2.011 Launch
rtxa5000-6.24.192.160.nvlink
262,144.0
pipeline
6 $3.50 1.454 Launch
h100nvl-1.16.96.160
262,144.0
1 $4.11 1.095 Launch
teslaa100-2.24.96.160.nvlink
262,144.0
tensor
2 $4.61 3.498 Launch
rtxa5000-8.24.256.160.nvlink
262,144.0
tensor
8 $4.61 1.848 Launch
h200-1.16.128.160
262,144.0
1 $4.74 2.885 Launch
teslaa100-2.24.256.160
262,144.0
tensor
2 $4.93 3.498 Launch
rtx5090-4.16.128.160
262,144.0
tensor
4 $5.74 2.021 Launch
rtx4090-6.44.256.160
262,144.0
pipeline
6 $5.83 1.610 Launch
rtx4090-8.44.256.160
262,144.0
tensor
8 $7.51 2.005 Launch
h100-2.24.256.160
262,144.0
tensor
2 $7.84 3.492 Launch
h200-2.24.256.160.nvlink
262,144.0
tensor
2 $9.40 8.140 Launch

Related models

Need help?

Contact our dedicated neural networks support team at nn@immers.cloud or send your request to the sales department at sale@immers.cloud.