Skip to main content
Nemotron 3.5
Large tier
Tool calling

Nemotron 3.5 Lightning 30B-A3B

NVIDIA's 30B/3B-active hybrid MoE for high-volume agent execution.

by NVIDIA

Nemotron 3.5 group

Overview

LoRA-only on Overmind via Unsloth. Native 256K context, Qwen-style tools, thinking off by default. Full FT disabled.

Nemotron 3.5 Lightning 30B-A3B 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

  • High-frequency tool-calling LoRA
  • Output validation and formatting specialists
  • Subagent routing in long-running agents
← Back to all models
Train now

Specs & cost

Cost to trainfrom $2.00
Cost to run (1M tok)from $6.00
GroupNemotron 3.5
FamilyNVIDIA
Parameters30B-A3B
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.