Skip to main content
Qwen 3.5
Large tier
Tool calling

Qwen 3.5 35B MoE

Large MoE Qwen 3.5: 35B total weights, 3B active per token at serve time.

by Qwen

Qwen 3.5 group

Overview

Qwen 3.5 is the default recommendation for most agents on Overmind. Every size shares a 256K inference context, tool calling starts at 0.8B, and the compact models train at their full 256K context, the longest trainable window in the catalogue.

Qwen 3.5 35B 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

  • Higher-quality Qwen 3.5 runs with MoE serve economics
  • Tool-calling agents that outgrow dense mid-tier bases
  • Side-by-side experiments against Qwen 3.5 27B

More in Qwen 3.5

← Back to all models
Train now

Specs & cost

Cost to trainfrom $2.50
Cost to run (1M tok)from $8.00
GroupQwen 3.5
FamilyQwen
Parameters35B MoE (3B active)
TierLarge
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.