CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.gpt-oss / gpt-oss-120b-4bit
From: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.gpt-ossSubject:

gpt-oss-120b-4bit

Date: 2026-11-15Commit: 08e7899Signed: 2DC28CC7B26A283B ✓

Text generation model with 116.8B parameters. Safetensors weights, 65.8 GB in all. Published by mlx-community under Apache-2.0.

116.8B params65.8GBgpt-oss-120b-4bitsafetensorspermissive
FactsParams116.8BSize65.8 GBFormatssafetensorsTasktext generationLicenseApache-2.0From sourcepermissive
$ fw get mlx-community/gpt-oss-120b-4bit
# manifest sha256 1906d43bcd75… · 65.8 GB · 22 files
$ fw verify ./gpt-oss-120b-4bit mlx-community/gpt-oss-120b-4bit
From sourceHosted (signed)mlx-community/gpt-oss-120b-4bitLast check: 2026-11-15 03:39 UTC
Run at homeGet help

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

Works with

Run24Fine-tune29Convert15Evaluate13Scan13Apps58
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
65.8 GB
Weights
65.8 GB (safetensors)
Parameters
116.8B
Formats
safetensors
Task
text generation
License
Apache-2.0 (permissive)
Files
22, each with a sha256
Publisher
mlx-community
Added
2026-11-15
Section
alt.freeweights.gpt-oss
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
BadgeHostLast checkResult
From sourcehuggingface.co2026-11-15 03:39 UTCpassed

Model card

From the publisher at commit 08e7899. Shown as plain text with links; images open at the publisher.

mlx-community/gpt-oss-120b-4bit#

This model mlx-community/gpt-oss-120b-4bit was converted to MLX format from None using mlx-lm version 0.26.3.

Use with mlx#

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/gpt-oss-120b-4bit")

prompt = "hello"

if tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)

Files

22 files · 65.8 GBWeights 65.8 GB (safetensors). Sizes and sha256 from the signed manifest.
Show all 22 files with their sha256
FileSizesha256
.gitattributes1.57 KB34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
README.md770 B817dca66c3e6e8c64f378ffb6042cb43829886379d70fd0055f68bc4439fd375
chat_template.jinja15.9 KBf8d9255777615591a7cc1a7c932f5a69e181128902295e1b81221d20d983cac7
config.json2.27 KBc39a8f2f6a7dc4f1188cfca31bd38312c5d14962cf77c6fa99bf712d3042e475
generation_config.json165 B199566674b96510c3b9a1141b494223a86a3ff83097e2c2f259c4d94fafc5847
model-00001-of-00013.safetensors5.15 GB6d61e9c197a7f18a3f78e8c5ddc86a3d3cb2299ec61cee8fc6550ed3142c8208
model-00002-of-00013.safetensors5.36 GB585d025ddebfa4d8da9cb776a192cda24027f99479fdbcc55e7321a2d0ba5ef2
model-00003-of-00013.safetensors4.90 GBa88a694c0eed9f63516bde70351186bed511e452e8774f3f6c0a160e985855cc
model-00004-of-00013.safetensors5.36 GB68985d43180d29f8d64fc28e4eca8779e3bd67f941b8d33b876c504720993265
model-00005-of-00013.safetensors4.90 GB9e9672b3a40c18c2300bb0f3e9bc803e68bd80f98583e556405a00d72d4ac3e5
model-00006-of-00013.safetensors5.34 GBc5e2991df6b66c07270b19eadf7a79f4d6949e0ee37d33338978aec664b68124
model-00007-of-00013.safetensors4.90 GBca428d9a23994c50f35965d60bc487325315dcd8188b3f36ad5af5ff1e88f3fa
model-00008-of-00013.safetensors5.36 GB0a11ee61e016e3bd55ad88cb25c16a6a7d8f59877abed2d49d042327f38b76de
model-00009-of-00013.safetensors4.90 GB6d6b302051d253b106778d38e2d1943fe93f95578f4cafdf33e7eb5c0e337b80
model-00010-of-00013.safetensors5.36 GB6891dae45de1ac295332ae17e444116d272196c5a715ddabc8b604cb21cd361f
model-00011-of-00013.safetensors4.90 GBc185ad8907180b5d6cb387918ed75bf4886563c6099a364d83a92ce49a1694bb
model-00012-of-00013.safetensors5.34 GBab2fc1e6a7ef9f3a4e954ada02caefb7e079f2f55362e75299152abcbb7ef5d0
model-00013-of-00013.safetensors4.01 GBf99813a191248a830e460c88957909e5b310d32efe8e1147522e0fc7b5b9a718
model.safetensors.index.json110 KB18d5f57b81630c1e401d832c3a04bba075549a15fbed7e7a7ae5532df8bd1d45
special_tokens_map.json440 B8464cabd6eda239fe46ebf8ae63b46c417721784a961a022f6b59174a2cda0e2
tokenizer.json27.9 MB0614fe83cadab421296e664e1f48f4261fa8fef6e03e63bb75c20f38e37d07d3
tokenizer_config.json4.20 KB9279e942392b742d633c7adbb89ebe002c98399db8926a7af5125c726f404070
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
08e7899579 pinned now2026-11-15 03:39 UTC22 files · 65.8 GB

Use it

$ fw get mlx-community/gpt-oss-120b-4bit
# manifest sha256 1906d43bcd75… · 65.8 GB · 22 files
$ fw verify ./gpt-oss-120b-4bit mlx-community/gpt-oss-120b-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/gpt-oss-120b-4bit.json --dir ./gpt-oss-120b-4bit $ python3 fw.py verify ./gpt-oss-120b-4bit ./mlx-community__gpt-oss-120b-4bit.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/gpt-oss-120b-4bit --revision 08e7899579b5dd5e0364e4bcd32578134072e22d --local-dir ./gpt-oss-120b-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/gpt-oss-120b-4bit", revision="08e7899579b5dd5e0364e4bcd32578134072e22d") model = AutoModelForCausalLM.from_pretrained("mlx-community/gpt-oss-120b-4bit", revision="08e7899579b5dd5e0364e4bcd32578134072e22d", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve mlx-community/gpt-oss-120b-4bit --revision 08e7899579b5dd5e0364e4bcd32578134072e22d
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
817dca66c3e6e8c64f378ffb6042cb43829886379d70fd0055f68bc4439fd375
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.gpt-ossSubject: gpt-oss-120b-4bitDate: 2026-11-15Commit: 08e7899Signed: 2DC28CC7B26A283B ✓
Upstream
mlx-community/gpt-oss-120b-4bit
Pinned commit
08e7899579b5dd5e0364e4bcd32578134072e22d
Manifest
gpt-oss-120b-4bit.json · .minisig
Manifest sha256
1906d43bcd756dac6bb1b6c5206bf313c07cc63aec6bc433515247a530b92c81
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 03:39 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/mlx-community/gpt-oss-120b-4bit.json $ curl -O https://freeweights.allternit.com/manifests/mlx-community/gpt-oss-120b-4bit.json.minisig $ minisign -Vm gpt-oss-120b-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/gpt-oss-120b-4bit
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. gpt-oss-120b-4bit.json. Provenance. Takedown history: none.
Source
huggingface.co/mlx-community/gpt-oss-120b-4bit

Related models

All of alt.freeweights.gpt-oss →
From: unsloth <huggingface.co/unsloth>Subject: gpt-oss-120b
From: unsloth <huggingface.co/unsloth>Subject: gpt-oss-120b-BF16
From: lmstudio-community <huggingface.co/lmstudio-community>Subject: gpt-oss-120b-GGUF
From: unsloth <huggingface.co/unsloth>Subject: gpt-oss-120b-GGUF
From: lmstudio-community <huggingface.co/lmstudio-community>Subject: gpt-oss-120b-MLX-8bit
From: mlx-community <huggingface.co/mlx-community>Subject: gpt-oss-120b-mxfp4-bf16