Model Catalog#
Explore the model families and sizes supported by the NVIDIA NeMo Customizer microservice.
Model Families#
View the available Llama models from Meta, ranging from 8 billion to 70 billion parameters.
View the available Phi models from Microsoft, designed for strong reasoning capabilities with efficient deployment.
Support Matrix#
The support matrices show the list of supported models and the features available for each model. For detailed technical specifications of each model (architecture, parameters, token limits, etc.), please refer to the previously listed model family pages.
Large Language Models#
Model |
Train a Chat Model |
Train a Chat Model with Tool Calling |
Train a Completion Model |
Fine-tuning Options |
Sequence Packing[1] |
Inference with NIM |
|---|---|---|---|---|---|---|
Yes |
Yes |
Yes |
LoRA |
No |
Supported (unverified) |
|
Yes |
Yes |
Yes |
SFT, LoRA |
Yes |
Supported (unverified) |
|
Yes |
Yes |
Yes |
SFT, LoRA |
Yes |
Supported |
|
Yes |
Yes |
Yes |
LoRA |
Yes |
Supported (unverified) |
|
Yes |
Yes |
Yes |
SFT, LoRA |
Yes |
Supported |
|
Yes |
Yes |
Yes |
LoRA |
Yes |
Supported (unverified) |
|
Yes |
No |
Yes |
SFT, LoRA |
No |
Not supported |
Embedding Models#
Model |
Fine-tuning Options |
Inference with NIM |
|---|---|---|
SFT |
Not supported |