# QuantFactory/Phi-3-mini-4k-instruct-GGUF

This model is a quantized text generation version of Phi 3 Mini 4K Instruct created with llama.cpp, and it is a 3.8B parameter decoder only Transformer. The card says it supports 4K context and is fine tuned with supervised fine tuning and direct preference optimization. The card also says the model was trained on 4.9T tokens and uses instruction following and safety post training.

## Cite this

- Page: https://huggingbay.xyz/artifact/hf-model-quantfactory-phi-3-mini-4k-instruct-gguf
- Citation: QuantFactory/Phi-3-mini-4k-instruct-GGUF. The Hugging Bay model record. https://huggingbay.xyz/artifact/hf-model-quantfactory-phi-3-mini-4k-instruct-gguf (retrieved 2026-11-17).
- 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-quantfactory-phi-3-mini-4k-instruct-gguf/files?limit=100. How checks work: https://huggingbay.xyz/verification

## Facts

- Type: LLM
- Task: text-generation
- Framework: unknown
- License: mit: Permissive open license: commercial use, modification, and redistribution are permitted. (https://spdx.org/licenses/MIT.html)
- Source: https://huggingface.co/QuantFactory/Phi-3-mini-4k-instruct-GGUF
- Hosting: hosted (1 file)
- Files: 1 hosted of 16 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: 1 hosted of 16 listed
- Full repo upstream: 34.2 GB
- Recommended file: 2.32 GB (Q4_K_M) · Phi-3-mini-4k-instruct.Q4_K_M.gguf
- Download: https://huggingbay.xyz/api/artifacts/hf-model-quantfactory-phi-3-mini-4k-instruct-gguf/download-plan (download plan: https://huggingbay.xyz/api/artifacts/hf-model-quantfactory-phi-3-mini-4k-instruct-gguf/download-plan)
- Per-file SHA-256: available for 1 of 1 hosted file via https://huggingbay.xyz/api/artifacts/hf-model-quantfactory-phi-3-mini-4k-instruct-gguf/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: 1044
- Stars: 6
- Card completeness: 92%

## Description

This model is a quantized text generation version of Phi 3 Mini 4K Instruct created with llama.cpp, and it is a 3.8B parameter decoder only Transformer. The card says it supports 4K context and is fine tuned with supervised fine tuning and direct preference optimization. The card also says the model was trained on 4.9T tokens and uses instruction following and safety post training.

## Model Card Facts

- Declared license: mit
- Pipeline: text-generation
- Library: unknown
- Task categories: text-generation
- Languages: en
- File hints: 16 upstream file samples

## File Hints

- .gitattributes (2.4 KB)
- Phi-3-mini-4k-instruct.Q2_K.gguf (1.3 GB) LFS
- Phi-3-mini-4k-instruct.Q3_K_L.gguf (1.9 GB) LFS
- Phi-3-mini-4k-instruct.Q3_K_M.gguf (1.7 GB) LFS
- Phi-3-mini-4k-instruct.Q3_K_S.gguf (1.6 GB) LFS
- Phi-3-mini-4k-instruct.Q4_0.gguf (2.0 GB) LFS
- Phi-3-mini-4k-instruct.Q4_1.gguf (2.2 GB) LFS
- Phi-3-mini-4k-instruct.Q4_K_M.gguf (2.2 GB) LFS
- Phi-3-mini-4k-instruct.Q4_K_S.gguf (2.0 GB) LFS
- Phi-3-mini-4k-instruct.Q5_0.gguf (2.5 GB) LFS
- Phi-3-mini-4k-instruct.Q5_1.gguf (2.7 GB) LFS
- Phi-3-mini-4k-instruct.Q5_K_M.gguf (2.5 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 2026-08-28T11:44:46.140Z.
- 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-quantfactory-phi-3-mini-4k-instruct-gguf
- Files API: https://huggingbay.xyz/api/artifacts/hf-model-quantfactory-phi-3-mini-4k-instruct-gguf/files?limit=100
- Metadata: https://huggingbay.xyz/api/artifacts/hf-model-quantfactory-phi-3-mini-4k-instruct-gguf/metadata.json
- Distribution: https://huggingbay.xyz/api/artifacts/hf-model-quantfactory-phi-3-mini-4k-instruct-gguf/distribution
- Manifest: https://huggingbay.xyz/api/manifests/hf-model-quantfactory-phi-3-mini-4k-instruct-gguf
- Download plan (per-file SHA-256 + signed download URLs): https://huggingbay.xyz/api/artifacts/hf-model-quantfactory-phi-3-mini-4k-instruct-gguf/download-plan
- Hosted download rows: https://huggingbay.xyz/api/downloadable-files?artifactId=hf-model-quantfactory-phi-3-mini-4k-instruct-gguf&limit=100
- Request mirror: not applicable.
- Submit peer fallback for review: POST https://huggingbay.xyz/api/artifacts/hf-model-quantfactory-phi-3-mini-4k-instruct-gguf/decentralized-fallbacks
