CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.phi / phi-4-8bit
From: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.phiSubject:

phi-4-8bit

Date: 2026-11-15Commit: 7a40ce2Signed: 2DC28CC7B26A283B ✓

Text generation model with 14.7B parameters. Safetensors weights, 15.6 GB in all. Published by mlx-community under MIT.

14.7B params15.6GBphi-4-8bitsafetensorspermissive
FactsParams14.7BSize15.6 GBFormatssafetensorsTasktext generationLicenseMITFrom sourcepermissive
$ fw get mlx-community/phi-4-8bit
# manifest sha256 d193fea7ffe0… · 15.6 GB · 12 files
$ fw verify ./phi-4-8bit mlx-community/phi-4-8bit
From sourceHosted (signed)mlx-community/phi-4-8bitLast check: 2026-11-15 05:10 UTC
Run at homeGet help

Get help: custom fine-tune or private deploy. We review your setup before we quote.

Quantized of phi-4.

Works with

Run24Fine-tune29Convert15Evaluate13Scan13Apps58
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
15.6 GB
Weights
15.6 GB (safetensors)
Parameters
14.7B
Formats
safetensors
Task
text generation
License
MIT (permissive)
Files
12, 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

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
BadgeHostLast checkResult
From sourcehuggingface.co2026-11-15 05:10 UTCpassed

Model card

From the publisher at commit 7a40ce2. Shown as plain text with links; images open at the publisher.

mlx-community/phi-4-8bit#

The Model mlx-community/phi-4-8bit was converted to MLX format from microsoft/phi-4 using mlx-lm version 0.20.6.

Use with mlx#

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/phi-4-8bit")

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

12 files · 15.6 GBWeights 15.6 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 12 files with their sha256
FileSizesha256
.gitattributes1.52 KB11ad7efa24975ee4b0c3c3a38ed18737f0658a5f75a0a96787b576a78a023361
README.md1.11 KB459052012bb8b654571e8d4afde074bbfc4bc85fa2e98e44dc855f38e8b7b2d8
config.json996 Bbff10a156ade41cc80a32dc63e9e465970d0ef0576be8b41c85d6562aa2452e3
merges.txt917 KBb6fe424e334903f7fb84d3a106d9730455f4744b9fe3c21ee136d97a00e72502
model-00001-of-00003.safetensors5.32 GB1fa0eb9b8ef0a1e6e36044481309843fde04e7b6b7a374c3814c1e9ef83ac408
model-00002-of-00003.safetensors5.36 GBbf7cc6910977e872cd1589c7b3a5b813040c166f28cd2f28cdf11acf5ca334e0
model-00003-of-00003.safetensors4.89 GB4106b9fb43727deb5cf8e2dc60fc6757128b7805627dee239119293b8fabada3
model.safetensors.index.json49.3 KBdec871a013e4a5e3215fc732b46b995898522b6ea3d346615619994f1ea363cc
special_tokens_map.json467 B7ab1bb39a61cece348c8d6c4bd258bfb7268a2dac5dcab4e3efe7204631234c1
tokenizer.json7.15 MBc612e57b2763204798271c0cdc14a373a565e6a371f1bfbd44e385a8391c9884
tokenizer_config.json17.7 KB9491440715ae486d8eba4cf91fea5ef32bca92f2aa6ea55976b6aba762897c6b
vocab.json1.61 MB741943243bd0035a8082ef0ccc09ef62e7ce7ec2f2f053aeedd808dba1c2ffc5
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
7a40ce2189 pinned now2026-11-15 05:10 UTC12 files · 15.6 GB

Use it

$ fw get mlx-community/phi-4-8bit
# manifest sha256 d193fea7ffe0… · 15.6 GB · 12 files
$ fw verify ./phi-4-8bit mlx-community/phi-4-8bit
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/mlx-community/phi-4-8bit.json --dir ./phi-4-8bit $ python3 fw.py verify ./phi-4-8bit ./mlx-community__phi-4-8bit.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/phi-4-8bit --revision 7a40ce2189ec31997a0f9bb949d60206f90527c8 --local-dir ./phi-4-8bit
transformersLoad 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-4-8bit", revision="7a40ce2189ec31997a0f9bb949d60206f90527c8") model = AutoModelForCausalLM.from_pretrained("mlx-community/phi-4-8bit", revision="7a40ce2189ec31997a0f9bb949d60206f90527c8", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve mlx-community/phi-4-8bit --revision 7a40ce2189ec31997a0f9bb949d60206f90527c8
Run at home

License

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
459052012bb8b654571e8d4afde074bbfc4bc85fa2e98e44dc855f38e8b7b2d8
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: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.phiSubject: phi-4-8bitDate: 2026-11-15Commit: 7a40ce2Signed: 2DC28CC7B26A283B ✓
Upstream
mlx-community/phi-4-8bit
Pinned commit
7a40ce2189ec31997a0f9bb949d60206f90527c8
Manifest
phi-4-8bit.json · .minisig
Manifest sha256
d193fea7ffe050d960fa7694b2173247777e5ceff6a2155171e52242fc20033e
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 05:10 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/mlx-community/phi-4-8bit.json $ curl -O https://freeweights.allternit.com/manifests/mlx-community/phi-4-8bit.json.minisig $ minisign -Vm phi-4-8bit.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

Parent

microsoft/phi-4 · this model is a quantization of it

No model in the catalog names this one as its parent.

Get it
Download
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/phi-4-8bit
Open in Freeweights Studio

Pull, verify and run it in the Allternit app on Desktop, web or phone.

Signed manifest
minisign, key 2DC28CC7B26A283B. phi-4-8bit.json. Provenance. Takedown history: none.
Source
huggingface.co/mlx-community/phi-4-8bit

Related models

All of alt.freeweights.phi →
From: BAAI <huggingface.co/BAAI>Subject: bunny-phi-2-siglip-lora
From: microsoft <huggingface.co/microsoft>Subject: MediPhi
From: microsoft <huggingface.co/microsoft>Subject: MediPhi-Clinical
From: microsoft <huggingface.co/microsoft>Subject: MediPhi-Guidelines
From: microsoft <huggingface.co/microsoft>Subject: MediPhi-Instruct
From: microsoft <huggingface.co/microsoft>Subject: MediPhi-MedCode