Skip to main content
Qwen 3
Mid tier
Tool calling

Qwen 3 Coder 30B MoE

Code-specialised Qwen 3 MoE with 256K context and tool calling.

by Qwen

Qwen 3 group

Overview

Qwen 3 Coder 30B is the code-specialised mixture-of-experts model in the Qwen 3 family: 30B total weights with 3B active per token, with a full 256K context for both inference and training. Train it on your agent's coding traces, then benchmark it against the model you run in production today.

Qwen 3 Coder 30B MoE trains on your agent's own traces with LoRA adapters or full finetuning, is benchmarked against your production model before any traffic moves, and serves through the same OpenAI-compatible API as every Overmind model. The final weights are yours to download and run anywhere.

Good for

  • Code generation and repair agents
  • Tool-calling engineering loops
  • MoE serve cost with a code-oriented base

More in Qwen 3

← Back to all models
Train now

Specs & cost

Cost to trainfrom $2.00
Cost to run (1M tok)from $8.00
GroupQwen 3
FamilyQwen
Parameters30B MoE (3B active)
TierMid
Context window256K
Max training context256K
Tool callingYes
Methods—
Train now
Training docs

On Overmind

  1. 01 Train on your data

    LoRA or full finetuning on a training-intent dataset from your agent's traces. Overmind recommends tiers from your data stats; you can edit every setting.

  2. 02 Benchmark vs production

    Each finished model is scored on your eval set with your rubric against the model your agent runs today. The headline is the baseline delta per metric.

  3. 03 Serve and own the weights

    Succeeded runs deploy automatically to Inference through the same OpenAI-compatible API. The final weights are yours to download and run anywhere.