From: <huggingface.co/mlx-community> Newsgroups: alt.freeweights.phiSubject: Phi-4-mini-instruct-4bit Date: 2026-11-15Commit: ac1c269Signed: 2DC28CC7B26A283B ✓ Text generation model with 3.8B parameters. Safetensors weights, 2.18 GB in all. Published by mlx-community under MIT.
3.8B params 2.18 GB Phi-4-mini-instruct-4bit safetensors permissive Facts Params 3.8B Size 2.18 GB Formats safetensors Task text generation License MIT permissive
fw
$ fw get mlx-community/Phi-4-mini-instruct-4bit
# manifest sha256 40bb318e8441… · 2.18 GB · 14 files
$ fw verify ./Phi-4-mini-instruct-4bit mlx-community/Phi-4-mini-instruct-4bitHosted (signed) mlx-community/Phi-4-mini-instruct-4bit Last check: 2026-11-15 04:57 UTC
Get help: custom fine-tune or private deploy. We review your setup before we quote.
Quantized of Phi-4-mini-instruct .
Works with
Runs with Ranked by fit to this model (safetensors), then by GitHub stars.
Show all 24 Fine-tune with Show all 29
Overview
Size 2.18 GB
Weights 2.16 GB (safetensors)
Parameters 3.8B
Formats safetensors
Task text generation
License MIT (permissive)
Files 14, each with a sha256
Publisher mlx-community
Added 2026-11-15
Section alt.freeweights.phi Lineage
Original release from the publisher.
Base model: microsoft/Phi-4-mini-instruct
Where these bytes come from
Publisher at the pinned commit →You
Sources are tried in order. A file counts only when its size and sha256 match the manifest. Sources are checked when you ask for them, not on a timer.
Sources
Badge Host Last check Result huggingface.co 2026-11-15 04:57 UTC passed
Model card From the publisher at commit
ac1c269 . Shown as plain text with links; images open at the publisher.
pcuenq/Phi-4-mini-instruct-Q4-mlx#
The Model pcuenq/Phi-4-mini-instruct-Q4-mlx was converted to MLX format from microsoft/Phi-4-mini-instruct using mlx-lm version 0.21.5 .
Use with mlx#
from mlx_lm import load, generate
model, tokenizer = load("pcuenq/Phi-4-mini-instruct-Q4-mlx")
prompt="hello"
if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
messages, tokenize=False, add_generation_prompt=True
)
response = generate(model, tokenizer, prompt=prompt, verbose=True)Files 14 files · 2.18 GB Weights 2.16 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 14 files with their sha256 File Size sha256 .gitattributes 1.57 KB 34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930 README.md 1.18 KB 712f2599b4ce2fe8515382b4d8131112083f106a34f09419776979fc78126ca5 added_tokens.json 249 B d4f2aceb0f20b71dd1f4bcc7e052e4412946bf281840b8f83d39f259571af486 config.json 3.30 KB 431eafdf55dc6d4a76dc3e9f22b0d06eac42d9ac6dc7cbd7ff8ca1e38f18cdb1 configuration_phi3.py 10.9 KB ec2044b77d0b8111640ac134daa3af1f40dc552a739f8959626e7e58ea3352df merges.txt 2.42 MB 856ce61180bb689282eed6b3a6838bb1f438399be23aefe9d20eb379791fb4ad model.safetensors 2.16 GB 9dcfcdc0a579494283f2d2317ad686123782ce461d1111690ede7c904ff3f87b model.safetensors.index.json 32.6 KB 958e2e0939857e9fb398e9e3d5344a84e345b00da2e4e7c396024d6a91bc1ab7 modeling_phi3.py 54.3 KB d5fd551a7fe759b1d25e5b16b5012aa98b9b8bd400d26c7ee69c0090a245d6cd sample_finetune.py 6.17 KB 50e6468a9b17566703fad95fa4ae7372fd4af1936e551f53bab0aa8b28e62cf5 special_tokens_map.json 587 B aff38493227d813e29fcf8406e8e90062f1f031aa47d589325e9c31d89ac7cc3 tokenizer.json 15.5 MB 382cc235b56c725945e149cc25f191da667c836655efd0857b004320e90e91ea tokenizer_config.json 2.96 KB 76c79ba1828e98a574123dd5de047587219ed8c1ab20702d340bc10a7a32b6bd vocab.json 3.91 MB 6cb65a857824fa6615bb1782d95d882617a8bbce1da0317118586b36f39e98bd
Versions Each time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commit Date Contents ac1c269cb4 pinned now 2026-11-15 04:57 UTC 14 files · 2.18 GB
Use it fw
$ fw get mlx-community/Phi-4-mini-instruct-4bit
# manifest sha256 40bb318e8441… · 2.18 GB · 14 files
$ fw verify ./Phi-4-mini-instruct-4bit mlx-community/Phi-4-mini-instruct-4bitfw.py Checks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/mlx-community/Phi-4-mini-instruct-4bit.json --dir ./Phi-4-mini-instruct-4bit
$ python3 fw.py verify ./Phi-4-mini-instruct-4bit ./mlx-community__Phi-4-mini-instruct-4bit.jsonhf The Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT =https://freeweights.allternit.com hf download mlx-community/Phi-4-mini-instruct-4bit --revision ac1c269cb4222a4e136a3d09edad301056c1f36a --local-dir ./Phi-4-mini-instruct-4bittransformers Load the weights in Python.
import os
os.environ["HF_ENDPOINT" ] = "https://freeweights.allternit.com"
from transformers import AutoModelForCausalLM, AutoTokenizer
tok = AutoTokenizer.from_pretrained("mlx-community/Phi-4-mini-instruct-4bit", revision="ac1c269cb4222a4e136a3d09edad301056c1f36a")
model = AutoModelForCausalLM.from_pretrained("mlx-community/Phi-4-mini-instruct-4bit", revision="ac1c269cb4222a4e136a3d09edad301056c1f36a", device_map="auto")vLLM Serve an OpenAI-compatible API.
$ HF_ENDPOINT =https://freeweights.allternit.com vllm serve mlx-community/Phi-4-mini-instruct-4bit --revision ac1c269cb4222a4e136a3d09edad301056c1f36aLicense Name MIT License Id MIT Class Permissive Redistribution yes Listing Hosted (signed) Decided License as declared by the publisher. No person read it. 2026-11-15 Text in README.md Text sha256 712f2599b4ce2fe8515382b4d8131112083f106a34f09419776979fc78126ca5 Terms gate No extra terms beyond the license. Read the license text
Licenses are checked against the license table . A custom license passes only after a person reads it.
Provenance From: <huggingface.co/mlx-community> Newsgroups: alt.freeweights.phiSubject: Phi-4-mini-instruct-4bit Date: 2026-11-15Commit: ac1c269Signed: 2DC28CC7B26A283B ✓ How to verify
$ curl -O https://freeweights.allternit.com/manifests/mlx-community/Phi-4-mini-instruct-4bit.json
$ curl -O https://freeweights.allternit.com/manifests/mlx-community/Phi-4-mini-instruct-4bit.json.minisig
$ minisign -Vm Phi-4-mini-instruct-4bit.json -P RWQ7KGqyx4zCLXtUFOqvfv8L3g+8fpKJ1FsuxPyOYMF+4KufbUxKq1Oq
$ shasum -a 256 <file> # compare with the Files tab A manifest whose signature fails must be rejected. A file whose size or sha256 does not match must be discarded. Verify a download
Model tree No model in the catalog names this one as its parent.
Get it
$ HF_ENDPOINT =https://freeweights.allternit.com hf download mlx-community/Phi-4-mini-instruct-4bitOpen in Freeweights Studio Pull, verify and run it in the Allternit app on Desktop, web or phone.
phi 400 MB bunny-phi-2-siglip-lora safetensors permissive Facts Params not stated Size 400 MB Formats safetensors Task text generation License Apache-2.0 permissive flip From: <huggingface.co/BAAI> Subject: bunny-phi-2-siglip-lora 3.8B params 7.64 GB MediPhi safetensors permissive Facts Params 3.8B Size 7.64 GB Formats safetensors Task text generation License MIT permissive flip From: <huggingface.co/microsoft> Subject: MediPhi 3.8B params 7.64 GB MediPhi-Clinical safetensors permissive Facts Params 3.8B Size 7.64 GB Formats safetensors Task text generation License MIT permissive flip From: <huggingface.co/microsoft> Subject: MediPhi-Clinical 3.8B params 7.64 GB MediPhi-Guidelines safetensors permissive Facts Params 3.8B Size 7.64 GB Formats safetensors Task text generation License MIT permissive flip From: <huggingface.co/microsoft> Subject: MediPhi-Guidelines 3.8B params 7.64 GB MediPhi-Instruct safetensors permissive Facts Params 3.8B Size 7.64 GB Formats safetensors Task text generation License MIT permissive flip From: <huggingface.co/microsoft> Subject: MediPhi-Instruct 3.8B params 7.64 GB MediPhi-MedCode safetensors permissive Facts Params 3.8B Size 7.64 GB Formats safetensors Task text generation License MIT permissive flip From: <huggingface.co/microsoft> Subject: MediPhi-MedCode
mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.phiSubject: 
BAAI