Tülu 3 8B

Overview

Allen AI's fully open post-training recipe applied to Llama 3.1 8B, hitting 87.6 on GSM8K with all data, code, and evals released publicly.

When to pick this model

• Reproducible research on RLHF and DPO pipelines
• Drop-in replacement for Llama 3.1 8B Instruct with stronger math
• Instruction-following workloads needing high IFEval scores
• Teams that need to audit training data end-to-end
• Academic baselines requiring full provenance

VRAM requirements by quantization

VRAM figures include model weights plus a typical 8k KV cache and ~600 MB runtime overhead (Ollama / llama.cpp baseline). Add headroom for higher context lengths.

Published benchmark scores

Scores published by the model author or aggregated from public leaderboards. Re-measured monthly by our editorial team.

Strengths

• Best fully-open RLHF recipe shipped to date
• GSM8K 87.6 is class-leading at 8B
• IFEval 82.4 shows strong instruction adherence
• Training data, code, and evals all publicly available
• Stable behavior on standard chat benchmarks

Limitations

• Inherits the Llama 3.1 Community License
• No native vision or tool-use specialization
• Eclipsed at the frontier by larger open models

Architecture & training

Architecture: Dense Llama 3.1 8B · SFT + DPO + RLVR

Training: Public data + code + evals.

Quick start

ollama run tulu3:8b

Or use the open-source MCP server to query this model from Claude Desktop, Cursor, or any MCP-compatible client.