Skip to main content
Llama 3
Small tier
Tool calling

Llama 3.1 8B Instruct

Small-tier Llama 3.1 with full 128K training context and tool calling.

by Meta

Llama 3 group

Overview

Llama 3 on Overmind covers Meta's instruct models at 1B, 3B, and 8B, each trainable at their full 128K context. Pick this family when your rows are long and you still want a compact model you can serve cheaply after training.

Llama 3.1 8B 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

  • Long-row training on compact bases
  • Meta-stack compatibility
  • Tool-calling agents at 1B through 8B

More in Llama 3

← Back to all models
Train now

Specs & cost

Cost to trainfrom $1.00
Cost to run (1M tok)from $6.00
GroupLlama 3
FamilyMeta
Parameters8B
TierSmall
Context window128K
Max training context128K
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.