Skip to main content
Qwen 3.8
Mid tier
Tool calling

Qwen 3.8 27B

Newest Qwen mid-tier base for coding and long-horizon agents you plan to own.

by Qwen

Qwen 3.8 group

Overview

Qwen 3.8 is the newest Qwen generation Overmind trains. Use it when you want the current Qwen coding and agent scores as a mid-tier base, then train LoRA on your agent's own traces.

Qwen 3.8 27B 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

  • Coding and long-horizon agent loops
  • Mid-tier quality before committing to a larger serve cost
  • Parallel experiments against Qwen 3.6 and 3.5 27B
← Back to all models
Train now

Specs & cost

Cost to trainfrom $2.00
Cost to run (1M tok)from $15.00
GroupQwen 3.8
FamilyQwen
Parameters27B
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.