3.1 8B Instruct
Llama 3Compact
Tool UseStructured Output
About this model
Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is fast and efficient. It has demonstrated strong performance compared to leading closed-source models in human evaluations. To read more about the model release, [click here](https://ai.meta.com/blog/meta-llama-3-1/). Usage of this model is subject to [Meta's Acceptable Use Policy](https://llama.meta.com/llama3/use-policy/).
Performance Tier
Compact
3.1 8B Instruct is a compact model from Llama 3 : optimized for speed and affordability.
Small, fast, and affordable. Optimized for speed and low cost, great for high-volume or simple tasks.
Pricing
This model is included in Elosia plans| Type | per 1M tokens |
|---|---|
| Input (prompt) | $0.020 |
| Output (completion) | $0.050 |
Capabilities
Context Length16K
Max Output Tokens16K
TokenizerLlama3
Inputtext
Outputtext
Release DateJuly 23, 2024
Benchmarks
General Intelligence
MMLU
69.4%
Mathematics
MATH-500
48%
Programming
HumanEval
72.6%
Recommended Use Cases
General ChatSummarizationCustomer Support
Strengths
- Very compact model ideal for edge and mobile deployment
- Lowest cost open model from Meta
- Fast inference suitable for real-time applications
- 128K context window despite small parameter count
Limitations
- Significantly limited reasoning and coding capabilities
- Not suitable for complex analysis or research tasks
Resources
This model may use your data for training
