Decision support
Dracarys Llama 3.1 70B Instruct vs Llama-Guard-3-8B
Compare canonical objects directly. The useful dimensions change with the object type, so model and hardware comparisons stay separate.
Benchmark results
No benchmark results have been matched to these models yet.
Model specifications
Release date
August 14, 2024
July 23, 2024
Context window
131K
128K
Native context
—
—
Max output tokens
131,072
4,096
Knowledge cutoff
—
2023-12
Open weights
Open weights
Open weights
Parameter count
70B
8B
API pricing · USD per 1M tokens
Input
—
—
Output
—
—
Cached input
—
—
Cache write
—
—
Capabilities and modalities
Input modalities
text
text
Output modalities
text
text
Tool calling
—
—
Reasoning option
—
—
Supported options
temperature
temperature
Capabilities
—
—
Architecture and availability
Architecture
—
—
Model families
—
—
Tokenizer
—
—
Instruction format
—
—
License
Llama 3 Community License
—
Providers
0
0
Provider endpoints
0
0
Ollama variants
0
0
Metadata source
models.dev
ai-research
A dash means the field is not reported. Provider-specific performance and pricing may differ.