alt.freeweights.phi / Phi-3.5-mini-instruct-4bit

From:

mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.phiSubject:

Phi-3.5-mini-instruct-4bit

Date: 2026-11-15Commit: 7b2052fSigned: 2DC28CC7B26A283B ✓

Text generation model with 3.8B parameters. Safetensors weights, 2.15 GB in all. Published by mlx-community under MIT.

3.8B params

2.15GBPhi-3.5-mini-instruct-4bitsafetensorspermissive

FactsParams3.8BSize2.15 GBFormatssafetensorsTasktext generationLicenseMITFrom sourcepermissive

$ fw get mlx-community/Phi-3.5-mini-instruct-4bit
# manifest sha256 900c41e2b701… · 2.15 GB · 13 files
$ fw verify ./Phi-3.5-mini-instruct-4bit mlx-community/Phi-3.5-mini-instruct-4bit

From sourceHosted (signed)mlx-community/Phi-3.5-mini-instruct-4bitLast check: 2026-11-15 02:48 UTC

Run at home Get help

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

Works with

Run24 Fine-tune29 Convert15 Evaluate13 Scan13 Apps58

Runs with

Ranked by fit to this model (safetensors), then by GitHub stars.

vLLM exo Text Generation WebUI

SGLang MLC LLM KTransformers LMCache Xinference LMDeploy mistral.rs Mooncake FlashInfer

Show all 24

AIBrix fastllm ExLlamaV3

Transformers LocalAI tinygrad gpu-unlock Triton Inference Server BentoML CTranslate2 ExLlamaV2 LitServe

Convert with

mergekit TensorRT Model Optimizer

LLM Compressor Neural Compressor AutoRound AQLM GPTQModel ONNX Core ML Tools ExecuTorch

Show all 15

Evaluate with

Opik DeepEval Ragas lm-evaluation-harness OpenCompass SWE-bench

simple-evals TruLens HELM

LightEval

Evaluate Weave

Show all 13

Autoevals

Scan with

promptfoo garak Guardrails NeMo Guardrails Giskard DeepTeam AI Fairness 360 Fairlearn Detoxify MCP Scanner AgentDojo ModelScan

Show all 13

picklescan

Overview Model card Files Use it License Provenance Model tree

Overview

Size: 2.15 GB
Weights: 2.15 GB (safetensors)
Parameters: 3.8B
Formats: safetensors
Task: text generation
License: MIT (permissive)
Files: 13, each with a sha256
Publisher: mlx-community
Added: 2026-11-15
Section: alt.freeweights.phi

Lineage

Original release from the publisher.

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
From source	huggingface.co	2026-11-15 02:48 UTC	passed

Model card

From the publisher at commit 7b2052f. Shown as plain text with links; images open at the publisher.

mlx-community/Phi-3.5-mini-instruct-4bit#

The Model mlx-community/Phi-3.5-mini-instruct-4bit was converted to MLX format from microsoft/Phi-3.5-mini-instruct using mlx-lm version 0.17.0.

Use with mlx#

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Phi-3.5-mini-instruct-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)

Files

13 files · 2.15 GBWeights 2.15 GB (safetensors). Sizes and sha256 from the signed manifest.

Hide all 13 files with their sha256

File	Size	sha256
.gitattributes	1.52 KB	11ad7efa24975ee4b0c3c3a38ed18737f0658a5f75a0a96787b576a78a023361
README.md	890 B	1c8c614c52ca8300267fc8be9980e281ac34eb3a44558456b3fe66a44f912585
added_tokens.json	293 B	5f5c94d30901fe9c961d776d51eadbda4454991a77b53d36e0be0571a8e72a7d
config.json	4.15 KB	6db0d08266c26038265c3a523917ff89214c4fd5893adbbb2cbca3128b9fa1d0
configuration_phi3.py	11.2 KB	d25f57c0823fcb9753880a25e79ab562b039d6187102ac13e4ff26dd11e9a81c
model.safetensors	2.15 GB	37e64496aa28fa5d5e4f29561f435defcbf6f7c8387f360c0aed45d37b93dfd7
model.safetensors.index.json	32.7 KB	4ef199a5c6c29fa54d84d3710bfad4b5424b75bbd68872f9e1e12234bd3fd9c3
modeling_phi3.py	73.8 KB	e737b46584be3ee907165eab54d8b18a18214acca4392a3ac9cbf37dbf9d3302
sample_finetune.py	6.13 KB	efb628083228e5248b7dff300e038964ea98b5c170c7544befa63b2675ae8491
special_tokens_map.json	569 B	474d699677e264edd3851559548cbbb61801ad8da6b249c81455007602313c34
tokenizer.json	1.84 MB	d0f067e1e15cd0a36ebef3668024882cb67a80b86fb4b7b4b128481f0d474db7
tokenizer.model	500 KB	9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
tokenizer_config.json	3.35 KB	cf1de23ab67807aed30e5145164c405c8c92890ca546112dd010de510fac3d1f

VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.

Upstream commit	Date	Contents
7b2052fd88 pinned now	2026-11-15 02:48 UTC	13 files · 2.15 GB

Use it

$ fw get mlx-community/Phi-3.5-mini-instruct-4bit
# manifest sha256 900c41e2b701… · 2.15 GB · 13 files
$ fw verify ./Phi-3.5-mini-instruct-4bit mlx-community/Phi-3.5-mini-instruct-4bit

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-3.5-mini-instruct-4bit.json --dir ./Phi-3.5-mini-instruct-4bit
$ python3 fw.py verify ./Phi-3.5-mini-instruct-4bit ./mlx-community__Phi-3.5-mini-instruct-4bit.json

hfThe Hugging Face CLI with one setting. Same repo id.

$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/Phi-3.5-mini-instruct-4bit --revision 7b2052fd882fe017300d4d42a4eb06a27b816af4 --local-dir ./Phi-3.5-mini-instruct-4bit

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-3.5-mini-instruct-4bit", revision="7b2052fd882fe017300d4d42a4eb06a27b816af4")
model = AutoModelForCausalLM.from_pretrained("mlx-community/Phi-3.5-mini-instruct-4bit", revision="7b2052fd882fe017300d4d42a4eb06a27b816af4", device_map="auto")

vLLMServe an OpenAI-compatible API.

$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve mlx-community/Phi-3.5-mini-instruct-4bit --revision 7b2052fd882fe017300d4d42a4eb06a27b816af4

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: 1c8c614c52ca8300267fc8be9980e281ac34eb3a44558456b3fe66a44f912585
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-3.5-mini-instruct-4bitDate: 2026-11-15Commit: 7b2052fSigned: 2DC28CC7B26A283B ✓

Upstream: mlx-community/Phi-3.5-mini-instruct-4bit
Pinned commit: 7b2052fd882fe017300d4d42a4eb06a27b816af4
Manifest: Phi-3.5-mini-instruct-4bit.json · .minisig
Manifest sha256: 900c41e2b701090fb0c792fee1ab38e7c9e60147dfb7f10efe17c3f436ee1fc3
Signature: minisign, Ed25519, key 2DC28CC7B26A283B
Created: 2026-11-15 02:48 UTC
Generator: freeweights-manifest/0.1.0
Takedowns: None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/mlx-community/Phi-3.5-mini-instruct-4bit.json
$ curl -O https://freeweights.allternit.com/manifests/mlx-community/Phi-3.5-mini-instruct-4bit.json.minisig
$ minisign -Vm Phi-3.5-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 related models in this catalog.Nothing here lists this model as its parent, and it names no parent.

Get it

Download

$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/Phi-3.5-mini-instruct-4bit

Open in Freeweights Studio

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

Signed manifest

minisign, key 2DC28CC7B26A283B. Phi-3.5-mini-instruct-4bit.json. Provenance. Takedown history: none.

Source

huggingface.co/mlx-community/Phi-3.5-mini-instruct-4bit

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

Phi-3.5-mini-instruct-4bit

Works with

Runs with

Fine-tune with

Convert with

Evaluate with

Scan with

Works with

Overview

Model card

mlx-community/Phi-3.5-mini-instruct-4bit#

Use with mlx#

Files

Use it

License

Provenance

How to verify

Model tree

Related models