Phi-4-mini-instruct
Support summary
Phi-4-mini-instruct is a checkpoint published by Microsoft, built on the Phi3ForCausalLM architecture. vLLM 0.28.0, the newest indexed vLLM release, documents support. TensorRT-LLM lists its architecture, but not this exact checkpoint.
vLLM documents support in 20 of 20 indexed releases, from 0.17.0 to 0.28.0.
- Documented hardware
- NVIDIA / CUDA
- Documented quantization
- BF16
- Configured context
- 131,072 tokens
- License
- mit
Hardware, quantization and features count only statements about this checkpoint; engine-wide capabilities are listed with each release.
Hugging Face model card
- Publisher
- Microsoft
- Task
- text generation
- License
- mit
- Library
- transformers
- Architecture
- Phi3ForCausalLM
- Weight tensor elements
- 3.8B
- Tensor types
- BF16
- Configured context
- 131,072 tokens
- Languages
- multilingual, ar, zh, cs, da, nl, en, fi, fr, de, he, hu, it, ja, ko, no, pl, pt, ru, es, sv, th, tr, uk
- Weight access
- Public
- Repository created
- 2025-02-19
Model notes and sources
- vLLM v0.28.0 · docs/models/supported_models.md · 20 indexed revisions, v0.17.0 to v0.28.0
- microsoft/Phi-4-mini-instruct · publisher model card
- microsoft/Phi-4-mini-instruct · Hugging Face metadata
- microsoft/Phi-4-mini-instruct · publisher configuration
- vllm · models/microsoft/Phi-4-mini-instruct.yaml
- vllm · Microsoft/Phi-4.md
- 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 | Architecture listed; exact checkpoint unknown | No supported release indexed | |
Features, dependencies and evidence for TensorRT-LLM 1.2.1 | ||||