✨ TuneLlama Beta Now Live
Effortless Llama 3.2
Fine-Tuning.
Upload your data. Choose 8B or 70B. Fine-tune.
Download your QLoRA adapters or GGUF file. It's that simple.
Pricing
Simple pricing by the token.
1B, 3B, 8B & 11B
$2.00 / million tokens
- Uses NVIDIA H100 GPU
- Download QLoRA adapters
- Download the GGUF q4_k_m
- Training files are deleted after training
70B & 90B
$4.00 / million tokens
- Uses NVIDIA H100 GPU
- Download QLoRA adapters
- Download the GGUF q4_k_m
- Training files are deleted after training
Enterprise
For larger runs and more bespoke training help, contact us directly.
Custom Pricing
- Custom model architecture
- Dedicated support
- Tailored training solutions
- Advanced fine-tuning options