Llama 3 8B Instruct
llama3-8b-instruct
About
The Llama 3 8B Instruct model, released on April 18, 2024, is Meta's latest instruction-following language model with 8 billion parameters. It utilizes an auto-regressive transformer architecture with Grouped-Query Attention for improved scalability. Trained on over 15 trillion tokens and fine-tuned with 10 million human-annotated examples, it excels in dialogue and conversational tasks. The model outperforms its predecessors on industry benchmarks, scoring 68.4 on MMLU (5-shot). Designed for commercial and research applications, it prioritizes safety and helpfulness, making it suitable for chatbots, virtual assistants, and other interactive AI applications. For more details, visit the Hugging Face page [1].
Llama 3 8B Instruct has a 8K-token context window.
Llama 3 8B Instruct input tokens at $0.03/1M, output at $0.04/1M.
Capabilities
Providers(17)
Compare all →| Provider | Input (per 1M) | Output (per 1M) | Type | |
|---|---|---|---|---|
| AWS Bedrock | $0.3 | $0.6 | Serverless | |
| DeepInfra | $0.05 | $0.15 | Serverless | |
| OctoAI API | $0.15 | $0.15 | Serverless | |
| Fireworks AI | $0.2 | $0.2 | Serverless | |
| Alibaba Cloud PAI-EAS | — | — | Serverless | |
| Baseten API | — | — | Serverless | |
| Lepton AI API | $0.07 | $0.07 | Serverless | |
| GCP Vertex AI | $0.12 | $0.36 | Serverless | |
| Cloudflare Workers AI | — | — | Serverless | |
| NVIDIA NIM | — | — | Provisioned | |
| Together AI | $0.18 | $0.18 | Serverless | |
| Perplexity Labs | $0.20 | $0.20 | Serverless | |
| Databricks Foundation Model Serving | — | — | Provisioned | |
| IBM watsonx | $0.6 | $0.6 | Serverless | |
| Microsoft Foundry | $0.37 | $1.1 | ServerlessProvisioned | |
| OpenRouter | $0.03 | $0.04 | Serverless | |
| Replicate API | $0.05 | $0.25 | Serverless |
Benchmark Scores(6)
| Benchmark | Score | Version | Source |
|---|---|---|---|
| Google-Proof Q&A | 44.8 | diamond | research |
| HellaSwag | 91.1 | 10-shot | research |
| HumanEval | 68.2 | pass@1 | research |
| Massive Multitask Language Understanding | 76.9 | 5-shot | research |
| Instruction-Following Evaluation | 59.5 | v2 | https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard |
| MMLU PRO | 40.5 | — | https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro |
