Models/llama-3-2-1b-instruct

llama-3-2-1b-instructActive · Cloud

IBM - Watsonx.ai · Released Sep 2024 · Llama Community License

Llama 3.2 1B is a 1-billion-parameter language model focused on efficiently performing natural language tasks, such as summarization, dialogue, and multilingual text analysis. Its smaller size allows it to operate...

Context
128K
Max output
128K
Input
$0.10
Output
$0.10
Cached in
-
Latency
-

Capabilities

Core
Streaming
Function calling
JSON mode
Structured outputs
Multimodal
Vision
Image input
Audio
Image generation
Video
Advanced
Reasoning
Tool calling
MCP
Prompt caching
Batch API
Embeddings

Benchmarks

BBH8.7
GPQA3.4
IFEval57
MATH Lvl 57
MMLU-Pro7.6
MUSR3
Open LLM Average14.4

Details

ReleasedSep 2024
LicenseLlama Community License
InputText
OutputText
Throughput-
Availability100%

Related models