Phi-4
Support summary
Phi-4 is a checkpoint published by Microsoft, built on the Phi3ForCausalLM architecture. The newest indexed releases vLLM 0.28.0 and TensorRT-LLM 1.2.1 both document support.
vLLM documents support in 20 of 20 indexed releases, from 0.17.0 to 0.28.0. TensorRT-LLM documents support in 2 of 2 indexed releases, from 1.2.0 to 1.2.1.
- Configured context
- 16,384 tokens
- License
- mit
Hugging Face model card
- Publisher
- Microsoft
- Task
- text generation
- License
- mit
- Library
- transformers
- Architecture
- Phi3ForCausalLM
- Weight tensor elements
- 14.7B
- Tensor types
- BF16
- Configured context
- 16,384 tokens
- Languages
- en
- Weight access
- Public
- Repository created
- 2024-12-11
Model notes and sources
Text-only Phi-4 is separate from Phi-4-multimodal and Phi-4-mini.
- vLLM v0.28.0 · docs/models/supported_models.md · 20 indexed revisions, v0.17.0 to v0.28.0
- TensorRT-LLM v1.2.1 · docs/source/models/supported-models.md · 2 indexed revisions, v1.2.0 to v1.2.1
- TensorRT-LLM v1.2.1 · docs/source/legacy/reference/support-matrix.md · 2 indexed revisions, v1.2.0 to v1.2.1
- microsoft/Phi-4 publisher metadata
- microsoft/phi-4 · publisher model card
- microsoft/phi-4 · Hugging Face metadata
- microsoft/phi-4 · publisher configuration
- Reviewed
Engine support
3 engines
| Engine | Release | Checkpoint support | Evidence scope | Last known supported |
|---|---|---|---|---|
| vLLM | 0.28.0Newest indexed | Checkpoint evidenceSource: vLLM v0.28.0 · docs/models/supported_models.mdReviewed | 0.28.0This release | |
Features, dependencies and evidence for vLLM 0.28.0 | ||||
| SGLang | 0.5.19Newest indexed | No matching evidence curated | No supported release indexed | |
Features, dependencies and evidence for SGLang 0.5.19 | ||||
| TensorRT-LLM | 1.2.1Newest indexed | Checkpoint evidenceSource 1: TensorRT-LLM v1.2.1 · docs/source/models/supported-models.mdSource 2: TensorRT-LLM v1.2.1 · docs/source/legacy/reference/support-matrix.mdReviewed | 1.2.1This release | |
Features, dependencies and evidence for TensorRT-LLM 1.2.1 | ||||