Skip to main content
Qwen 2.5
Large tier
Tool calling

Qwen 2.5 Coder 32B Instruct

Dedicated Qwen 2.5 coder at 32B for code agents already on this family.

by Qwen

Qwen 2.5 group

Overview

Qwen 2.5 Coder 32B Instruct is the dedicated coder in the mature Qwen 2.5 line. Keep it when your coding agent or eval harness is already tuned around Qwen 2.5 and you want controlled training rather than moving families.

Qwen 2.5 Coder 32B Instruct 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 agents already on Qwen 2.5
  • Tool-calling engineering workflows
  • Stable baselines before a family upgrade

More in Qwen 2.5

← Back to all models
Train now

Specs & cost

Cost to trainfrom $2.25
Cost to run (1M tok)from $20.00
GroupQwen 2.5
FamilyQwen
Parameters32B
TierLarge
Context window128K
Max training context32K
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.