LLM Lab
Search
Data Collection
Architecture
Training
Inference
Evals & Testing
AI/ML Quiz
Focus Play
Playground
AI/ML Dictionary
ZeroCasting

Model Configuration

Configure your deployment. Balance accuracy against cost and latency.

Parameter Count (Billions)
1B
Precision (Quantization)
16-bit
Accuracy (MMLU)
9.5%
Inference Speed
100 tok/s
Est. Hourly Cost
0.50 $/hr
MODEL
PreviousTraining
NextEvals & Testing