Phi-4-cuda-gpu · azureml v2 ↗
- source model id
- azureml/Phi-4-cuda-gpu@2
- hosting
- foundry-local-or-optimized
- platforms
- Microsoft Foundry
- license
- MIT
- max output tokens
- 2048
- architecture
- input_modalities
- text
- output_modalities
- text
- capabilities
This model is an optimized version of Phi-4 to enable local inference on CUDA GPUs. This model uses RTN quantization. # Model Description - **Developed by:** Microsoft - **Model type:** ONNX - **Lice…
azureFoundry/azureml/Phi-4-cuda-gpu@2
This model is an optimized version of Phi-4 to enable local inference on CUDA GPUs. This model uses RTN quantization.
See Hugging Face model Phi-4 for details.
1–1 / 1
1–1 / 1
1–3 / 3
Microsoft Foundry · Model page ↗
1–1 / 1
These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.