Llama 3.1 8B

Meta llm

Small sibling of the 3.1 family.

overall ⌄

—

nothing published

price · $/M tokens

self-hosted

open weights, no first-party API

to run it yourself ⌄

5 GB

minimum · 19 GB recommended

HF ↗ Ollama ↗ HuggingFace ↗

Benchmarks

What its maker published, and what anyone else measured. Every figure links the document it came from.

benchmark	published	measured
MMLU-Pro	—	47.6
GPQA	—	25.9
AIME 2025	—	4.3
HLE	—	5.1

Lineage

↓ base DeepSeek R1 Distill Llama 8B

↓ finetune Hermes 3 Llama 3.1 8B

↓ finetune Llama 3.1 8B Instruct

↓ distill Llama 3.2 3B Instruct

view in full graph →

Metadata

org	Meta
released	2024-07-23
params	8B
license	llama-3.1
hf id	meta-llama/Llama-3.1-8B