MetaLlama 3Open SourceArena #225Apr 18, 2024

Meta: Llama 3 8B Instruct

Meta's latest class of model (Llama 3) launched with a variety of sizes & flavors. This 8B instruct-tuned version was optimized for high quality dialogue usecases. It has demonstrated strong performance compared to leading closed-source models in human evaluations. To read more about the model release, click here. Usage of this model is subject to Meta's Acceptable Use Policy.

Context Window
8K
tokens
Max Output
16K
tokens
Released
Apr 18, 2024
Arena Rank
#225
of 305 models

Capabilities

👁Vision
🧠Reasoning
🔧Tool Calling
Prompt Caching
🖥Computer Use
🎨Image Generation

Supported Parameters

Frequency Penalty
Reduce repetition
Logit Bias
Adjust token weights
Max Tokens
Output length limit
min_p
Presence Penalty
Encourage new topics
Repetition Penalty
Penalize repeated tokens
Response Format
JSON mode / structured output
Seed
Deterministic outputs
Stop Sequences
Custom stop tokens
Temperature
Controls randomness
Tool Choice
Control tool usage
Tool Calling
Function calling support
Top K
Top-K sampling
Top P
Nucleus sampling

Pricing Comparison

RouterInput / 1MOutput / 1MCached Input / 1M
OpenRouter$0.03$0.04
Martian$0.03$0.04
DeepInfra$0.03$0.04

Benchmarks

Open LLM Leaderboard
AverageOpen LLM Leaderboard
23.91/100
IFEvalOpen LLM Leaderboard
74.08/100
BBHOpen LLM Leaderboard
28.24/100
MATH Lvl 5Open LLM Leaderboard
8.69/100
GPQAOpen LLM Leaderboard
1.23/100
MUSROpen LLM Leaderboard
1.6/100
MMLU-PROOpen LLM Leaderboard
29.6/100

Model IDs

OpenRoutermeta-llama/llama-3-8b-instruct

Tags

tool-calling
Compare with another model

Related Models