HuggingFace Model Slug
HF Token (gated models)
🔍 Fetch
Use manual parameter count
Parameters (Billions)
Format
Context Length (tokens)
Batch Size
↺
1
64
LoRA Rank (r)
↺
4
256
GPU / Accelerator
Number of GPUs
↺
1
32
⚡ Calculate VRAM
🚀 Inference
🎓 Full Fine-Tune
🔧 LoRA
⚡ QLoRA
🚀 Inference
🎓 Full Fine-Tune
🔧 LoRA
⚡ QLoRA
📐 Formulas
▼
💡 Examples
▼