Llama 3.2 Instruct 3B: Quality, Performance & Price Analysis
Analysis of Meta's Llama 3.2 Instruct 3B and comparison to other AI models across key metrics including quality, price, performance (tokens per second & time to first token), context window & more. Click on any model to compare API providers for that model. For more details including relating to our methodology, see our FAQs.
Comparison Summary
Quality:
Llama 3.2 3B is of lower quality compared to average, with Quality Index across evaluations of 47.
Price:Llama 3.2 3B is cheaper compared to average with a price of $0.08 per 1M Tokens (blended 3:1).
Llama 3.2 3B Input token price: $0.07, Output token price: $0.08 per 1M Tokens.
Speed:Llama 3.2 3B Input token price: $0.07, Output token price: $0.08 per 1M Tokens.
Llama 3.2 3B is faster compared to average, with a output speed of 202.0 tokens per second.
Latency:Llama 3.2 3B has a lower latency compared to average, taking 0.34s to receive the first token (TTFT).
Context Window:Llama 3.2 3B has a smaller context windows than average, with a context window of 130k tokens.
Highlights
Quality
Artificial Analysis Quality Index; Higher is better
Speed
Output Tokens per Second; Higher is better
Price
USD per 1M Tokens; Lower is better
Parallel Queries:
Prompt Length:
Further details
o1-preview
Gemini 1.5 Pro (Sep '24)
Claude 3.5 Sonnet (Oct '24)
Mistral Large 2
Command-R+ (Aug '24)
Sonar 3.1 Small
Phi-3 Medium Instruct 14B
Solar Pro
DBRX Instruct
Llama 3.1 Nemotron Instruct 70B
Reka Flash (Sep '24)
Jamba 1.5 Large
DeepSeek-Coder-V2
Qwen2.5 Instruct 72B
Yi-Large
OpenChat 3.5 (1210)