CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.text / magnum-v4-72b-4bit
From: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.textSubject:

magnum-v4-72b-4bit

Date: 2026-11-15Commit: 8c5ef31Signed: 2DC28CC7B26A283B ✓

Text generation model with 72.7B parameters. Safetensors weights, 40.9 GB in all. Published by mlx-community under Apache-2.0.

72.7B params40.9GBmagnum-v4-72b-4bitsafetensorspermissive
FactsParams72.7BSize40.9 GBFormatssafetensorsTasktext generationLicenseApache-2.0From sourcepermissive
$ fw get mlx-community/magnum-v4-72b-4bit
# manifest sha256 fdbf90e41da6… · 40.9 GB · 18 files
$ fw verify ./magnum-v4-72b-4bit mlx-community/magnum-v4-72b-4bit
From sourceHosted (signed)mlx-community/magnum-v4-72b-4bitLast check: 2026-11-15 05:17 UTC
Run at homeGet help

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

Quantized of magnum-v4-72b.

Works with

Run24Fine-tune29Convert15Evaluate13Scan13Apps58
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
40.9 GB
Weights
40.9 GB (safetensors)
Parameters
72.7B
Formats
safetensors
Task
text generation
License
Apache-2.0 (permissive)
Files
18, each with a sha256
Publisher
mlx-community
Added
2026-11-15
Section
alt.freeweights.text
Lineage

Original release from the publisher.

Base model: anthracite-org/magnum-v4-72b

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 05:17 UTCpassed

Model card

From the publisher at commit 8c5ef31. Shown as plain text with links; images open at the publisher.

mlx-community/magnum-v4-72b-4bit#

The Model mlx-community/magnum-v4-72b-4bit was converted to MLX format from anthracite-org/magnum-v4-72b using mlx-lm version 0.20.4.

Use with mlx#

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/magnum-v4-72b-4bit")

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

18 files · 40.9 GBWeights 40.9 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 18 files with their sha256
FileSizesha256
.gitattributes1.57 KB34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
README.md1.22 KB7b55ba62154e17b9a6cda57dc2ad81cbad386aa0adc290c2fdf6eda422205b8a
added_tokens.json605 B58b54bbe36fc752f79a24a271ef66a0a0830054b4dfad94bde757d851968060b
config.json838 Bc1e933b7c1848abc749e2df6bcec486093971b38620ce574a47a5ce367e90d56
merges.txt1.67 MB8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5
model-00001-of-00008.safetensors5.37 GB5941c25101e4ee073088880250303c23bfcee1c34895d94a30d1d9853a71ba3a
model-00002-of-00008.safetensors5.29 GB34aceaaa2700b33e4f3e19aa4dcc2717d279418efcbd4a5333b3084a31ce964b
model-00003-of-00008.safetensors5.35 GB08125f66cc04f7aba54fdd12db1871010307f8bb01debd5f9ea4897eecfde306
model-00004-of-00008.safetensors5.29 GB9c4adf065c11cd36382d3ea5271975ac84901f9db66a7d9a8c87bcd3a675c80c
model-00005-of-00008.safetensors5.29 GBa42145df1d91b248886a7b543cbeb6c568ebc5799f1ae6920e1a82869719d119
model-00006-of-00008.safetensors5.29 GBd9128e8565b5e0578a04f13439ad08c3661e17f9fb90151e8df23c0a567e44a9
model-00007-of-00008.safetensors5.35 GB08afe42b8a56a1f31f9c5e4e0844bfe4e6b0170ef467b46ea0955f94a760780c
model-00008-of-00008.safetensors3.66 GB0544e0b3148df4cee98038ead6beb4e754ddd9436a7df056fe0d3a61666ae1ed
model.safetensors.index.json179 KBb357714b2314bcd2cd1d1fd3cbfde06f9e8b25d3029d6085cf27eba3ebb7170f
special_tokens_map.json613 B76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd
tokenizer.json11.4 MB9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
tokenizer_config.json7.34 KB5ad86497e7e95dd8af2e178f03719fe21d04bd138532337e1a185b6fe9eb0dd2
vocab.json2.78 MBca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
8c5ef3197e pinned now2026-11-15 05:17 UTC18 files · 40.9 GB

Use it

$ fw get mlx-community/magnum-v4-72b-4bit
# manifest sha256 fdbf90e41da6… · 40.9 GB · 18 files
$ fw verify ./magnum-v4-72b-4bit mlx-community/magnum-v4-72b-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/magnum-v4-72b-4bit.json --dir ./magnum-v4-72b-4bit $ python3 fw.py verify ./magnum-v4-72b-4bit ./mlx-community__magnum-v4-72b-4bit.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/magnum-v4-72b-4bit --revision 8c5ef3197ee0476c28ee458e5be0713a3aebb443 --local-dir ./magnum-v4-72b-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/magnum-v4-72b-4bit", revision="8c5ef3197ee0476c28ee458e5be0713a3aebb443") model = AutoModelForCausalLM.from_pretrained("mlx-community/magnum-v4-72b-4bit", revision="8c5ef3197ee0476c28ee458e5be0713a3aebb443", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve mlx-community/magnum-v4-72b-4bit --revision 8c5ef3197ee0476c28ee458e5be0713a3aebb443
Run at home

License

Name
Apache License 2.0
Id
Apache-2.0
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
7b55ba62154e17b9a6cda57dc2ad81cbad386aa0adc290c2fdf6eda422205b8a
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.textSubject: magnum-v4-72b-4bitDate: 2026-11-15Commit: 8c5ef31Signed: 2DC28CC7B26A283B ✓
Upstream
mlx-community/magnum-v4-72b-4bit
Pinned commit
8c5ef3197ee0476c28ee458e5be0713a3aebb443
Manifest
magnum-v4-72b-4bit.json · .minisig
Manifest sha256
fdbf90e41da63ea2b04a67d37fcc4af03469264a3b03423a55223eb19fae8173
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 05:17 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/mlx-community/magnum-v4-72b-4bit.json $ curl -O https://freeweights.allternit.com/manifests/mlx-community/magnum-v4-72b-4bit.json.minisig $ minisign -Vm magnum-v4-72b-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

Parent

anthracite-org/magnum-v4-72b · 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/magnum-v4-72b-4bit
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. magnum-v4-72b-4bit.json. Provenance. Takedown history: none.
Source
huggingface.co/mlx-community/magnum-v4-72b-4bit

Related models

All of alt.freeweights.text →
From: laion <huggingface.co/laion>Subject: a2-rl-e2egit_large-50-32B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_e2egit-large-15-8B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_e2egit-v2-10-8B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_pymethods2test-large-80-8B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_unitsyn-python-large-10-8B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_mix_h2_language_proportional-65-8B