MA
Meta AI
Language model · United States ·Apr 2024

Llama 3-8B

Language Open (Restricted)
8B
Parameters
19
Benchmarks

About Llama 3-8B

Llama 3-8B is an AI model developed by Meta AI, in the language category, released in 2024, made available as an open-weights model with 8B params.

On this page you'll find Llama 3-8B's full specifications, including 19 benchmark results. Review provider pricing and benchmark scores below, or compare Llama 3-8B head-to-head with other language models.

Links

Run Llama 3-8B locally — what to buy

Share this build ↗

Sized to what Llama 3-8B actually needs (~8k context at Q4), not to the biggest GPU: Good = cheapest that runs it, Better = best value, Best = most headroom. Speed is a hardware estimate; anything past ~120 tok/s is shown as instant.

Software support

✓ measured · · compatible · — not supported. Informational only — speed is hardware-based.

Community

Would you run Llama 3-8B again?
No votes yet — be the first.
Did it run? — community reports by hardware

No reports yet. Own this model on some hardware? Be the first to confirm it runs.

Discussion

No comments yet. Start the discussion.

Llama 3-8B benchmark scores
Benchmark Category Score Variant
HumanEval code 33.5% base-cited-qwen2-7b
MBPP code 53.9% base-cited-qwen2-7b
C-Eval general 49.5% base-cited-qwen2-7b
IFEval general 14.55% cited-falcon-mamba
MMLU general 66.7% base-cited-falcon-mamba
MMLU-Pro general 35.4% base-cited-qwen2-7b
MMLU-Pro general 24.55% cited-falcon-mamba
ARC-Challenge knowledge 60.24 base-cited-falcon-mamba
CMMLU knowledge 50.8 base-cited-qwen2-7b
GSM8K math 56% base-cited-qwen2-7b
GSM8K math 45.19% base-cited-falcon-mamba
MATH math 20.5% base-cited-qwen2-7b
BIG-Bench Hard reasoning 57.7% base-cited-qwen2-7b
BIG-Bench Hard reasoning 24.5% cited-falcon-mamba
GPQA Diamond reasoning 25.8% base-cited-qwen2-7b
GPQA Diamond reasoning 7.38% cited-falcon-mamba
HellaSwag reasoning 82.23 base-cited-falcon-mamba
Winogrande reasoning 78.45 base-cited-falcon-mamba
TruthfulQA safety 42.93% base-cited-falcon-mamba

More models like Llama 3-8B

Frequently asked questions

What is Llama 3-8B?

Llama 3-8B is an AI model developed by Meta AI, in the language category, released in 2024. It is tracked on GenAIList with its specifications, benchmark scores and provider pricing.

Who created Llama 3-8B?

Llama 3-8B was developed by Meta AI and released in 2024.

Is Llama 3-8B open source or proprietary?

Llama 3-8B ships as an open-weights model: you can download and self-host the weights, though the licence may place some restrictions on use.

How much does Llama 3-8B cost?

Pricing for Llama 3-8B depends on the provider. See the providers table on this page for the latest API rates.

How does Llama 3-8B perform on benchmarks?

Llama 3-8B is benchmarked across 19 evaluations on GenAIList, including HumanEval (33.5%). See the full benchmark table below and compare it with other models.

No videos yet. Know a good one? Add it below.

Know a great video about Llama 3-8B?