# microsoft/Phi-tiny-MoE-instruct

This model is a lightweight mixture of experts decoder only Transformer with 3.8B total parameters and 1.1B activated parameters. It uses a 32,064 vocabulary tokenizer, accepts text in chat format, and generates text with a 4k token context length.

## Cite this

- Page: https://huggingbay.xyz/artifact/hf-model-microsoft-phi-tiny-moe-instruct
- Citation: microsoft/Phi-tiny-MoE-instruct. The Hugging Bay model record. https://huggingbay.xyz/artifact/hf-model-microsoft-phi-tiny-moe-instruct (retrieved 2026-11-13).
- Check a downloaded file: run `shasum -a 256 <file>` (macOS), `sha256sum <file>` (Linux) or `Get-FileHash -Algorithm SHA256 <file>` (Windows), then compare with that file's SHA-256 at https://huggingbay.xyz/api/artifacts/hf-model-microsoft-phi-tiny-moe-instruct/files?limit=100. How checks work: https://huggingbay.xyz/verification

## Facts

- Type: LLM
- Task: text-generation
- Framework: transformers
- License: mit: Permissive open license: commercial use, modification, and redistribution are permitted. (https://huggingface.co/microsoft/Phi-tiny-MoE-instruct/blob/main/LICENSE)
- Source: https://huggingface.co/microsoft/Phi-tiny-MoE-instruct
- Hosting: hosted (15 files)
- Files: 15 hosted of 19 listed
- Needs its own code to run: Uses custom model code (configuration_slimmoe.py). Plain llama.cpp, Ollama and LM Studio commands are not offered for this model unless a GGUF file is listed.
- File counts: "listed" is every file in the source repository; only hosted files download from Hugging Bay, and the download plan lists the files it selects for one download, so its count can differ.
- Hosted here: 15 hosted of 19 listed
- Full repo upstream: 7.51 GB
- Recommended file: 7.51 GB (2 files)
- Download: https://huggingbay.xyz/api/artifacts/hf-model-microsoft-phi-tiny-moe-instruct/download-plan (download plan: https://huggingbay.xyz/api/artifacts/hf-model-microsoft-phi-tiny-moe-instruct/download-plan)
- Per-file SHA-256: available for 15 of 15 hosted files via https://huggingbay.xyz/api/artifacts/hf-model-microsoft-phi-tiny-moe-instruct/files?limit=100
- Availability: Ready
- Downloadable: yes
- Run-ready: no (Hugging Bay has not certified a run path for this model; hosted bytes are downloadable and hash-checkable only)
- Peer-assisted fallbacks: 0 verified, 0 pending review
- Downloads: 831711
- Stars: 41
- Card completeness: 92%

## Description

This model is a lightweight mixture of experts decoder only Transformer with 3.8B total parameters and 1.1B activated parameters. It uses a 32,064 vocabulary tokenizer, accepts text in chat format, and generates text with a 4k token context length.

## Model Card Facts

- Declared license: mit
- Pipeline: text-generation
- Library: transformers
- Task categories: text-generation
- Languages: en
- Paper ids: 2506.18349, 2404.14219, 2409.12136
- File hints: 16 upstream file samples

## Referenced Data

- Paper: 2506.18349
- Paper: 2404.14219
- Paper: 2409.12136

## File Hints

- .gitattributes (1.5 KB)
- CODE_OF_CONDUCT.md (444 B)
- LICENSE (1.1 KB)
- NOTICE.md (1.7 KB)
- README.md (13 KB)
- SECURITY.md (2.6 KB)
- added_tokens.json (315 B)
- config.json (1.0 KB)
- configuration_slimmoe.py (12 KB)
- data_summary_card.md (4.2 KB)
- generation_config.json (177 B)
- model-00001-of-00002.safetensors (4.7 GB) LFS

## Quality Checklist

- Summary: passed
- Description: passed
- Model card metadata: passed
- License: passed
- Provenance: passed
- File inventory: passed
- Hosted bytes: passed
- Scan result: passed
- Manifest signature: passed

## Safety Notes

- External catalog metadata imported from Hugging Face public API on 2026-08-28T02:08:33.376Z.
- Open license detected as mit.
- Not a run kit: hosted, hash-checked bytes only; run readiness is not certified for this model yet.

## Actions

- Web: https://huggingbay.xyz/artifact/hf-model-microsoft-phi-tiny-moe-instruct
- Files API: https://huggingbay.xyz/api/artifacts/hf-model-microsoft-phi-tiny-moe-instruct/files?limit=100
- Metadata: https://huggingbay.xyz/api/artifacts/hf-model-microsoft-phi-tiny-moe-instruct/metadata.json
- Distribution: https://huggingbay.xyz/api/artifacts/hf-model-microsoft-phi-tiny-moe-instruct/distribution
- Manifest: https://huggingbay.xyz/api/manifests/hf-model-microsoft-phi-tiny-moe-instruct
- Download plan (per-file SHA-256 + signed download URLs): https://huggingbay.xyz/api/artifacts/hf-model-microsoft-phi-tiny-moe-instruct/download-plan
- Hosted download rows: https://huggingbay.xyz/api/downloadable-files?artifactId=hf-model-microsoft-phi-tiny-moe-instruct&limit=100
- Request mirror: not applicable.
- Submit peer fallback for review: POST https://huggingbay.xyz/api/artifacts/hf-model-microsoft-phi-tiny-moe-instruct/decentralized-fallbacks