CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.gpt-oss / gpt-oss-20b
From: openai <huggingface.co/openai>Newsgroups: alt.freeweights.gpt-ossSubject:

gpt-oss-20b

Date: 2026-11-14Commit: 6cee5e8Signed: 2DC28CC7B26A283B ✓

Text generation model with 20.9B parameters. Safetensors weights, 41.3 GB in all. Published by openai under Apache-2.0.

20.9B params41.3GBgpt-oss-20bsafetensorspermissive
FactsParams20.9BSize41.3 GBFormatssafetensorsTasktext generationLicenseApache-2.0From sourcepermissive
$ fw get openai/gpt-oss-20b
# manifest sha256 0a3d3192b6cf… · 41.3 GB · 18 files
$ fw verify ./gpt-oss-20b openai/gpt-oss-20b
From sourceopenai/gpt-oss-20bLast check: 2026-11-14 06:31 UTC
Runs withvLLMSGLangFine-tune withAxolotlTRLPEFTUnsloth
OverviewFilesUse itLicenseProvenance

Overview

Size
41.3 GB
Weights
27.5 GB (safetensors)
Parameters
20.9B
Formats
safetensors
Task
text generation
License
Apache-2.0 (permissive)
Files
18, each with a sha256
Publisher
openai
Added
2026-11-14
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.co2026-11-14 06:31 UTCpassed

Files

18 files · 41.3 GBWeights 27.5 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 18 files with their sha256
FileSizesha256
.gitattributes1.57 KB34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
LICENSE11.4 KB58d1e17ffe5109a7ae296caafcadfdbe6a7d176f0bc4ab01e12a689b0499d8bd
README.md7.09 KB03c2fcf292549176757b85c911e7dcf527aef3e4241d64b6caec94af3ecf3ac2
USAGE_POLICY200 Bd6387ef7985019c45db8d9801e6ac5fd9f98f02b9f1c56f8c5af80c3e8f385d0
chat_template.jinja16.7 KBa4c9919cbbd4acdd51ccffe22da049264b1b73e59055fa58811a99efbd7c8146
config.json1.81 KB3a2a26ded679375b7928ddeca59764df7cea83220c1961035f6d6e232659e9ce
generation_config.json177 Bf9970ada892d2d1f72e3ed0a6535ccebadd11897318794ca671d8c7014c957da
metal/model.bin13.8 GB725b7f996b5a226d922f034a731aefc398652f670dcafc2efd78620509a0fef1
model-00000-of-00002.safetensors4.79 GB16d0f997dcfc4462089d536bffe51b4bcea2f872f5c430be09ef8ed392312427
model-00001-of-00002.safetensors4.80 GB4fbe328ab445455d6f58dc73852b85873bd626986310abd91cd4d2ce3245eaea
model-00002-of-00002.safetensors4.17 GBa18106b209e9ab35c3406db4f6f12a927364a058b21e9d1373d682e20674b303
model.safetensors.index.json36.4 KB0e085b977c4c9942f85938828e8c989ed7d5cdabf852e4da6a67c116cd502cd1
original/config.json376 B317522155fc243327ee341857d0c752d0094a0817e0e9aee2890d5ad8e009e04
original/dtypes.json13.1 KB566c9e6aded8957f41f1589cabaf73e39f2d1fcda3351d63efdfb7e9e78d376b
original/model.safetensors13.8 GB3340a61d1a0391e8c5b5d3463d18d4c48129a84bbc04a554c762c99020aa06ed
special_tokens_map.json98 Bdd5e191d20c12d2fee1da5bae14ca1db0f5f4215300af691f23cdee97120a293
tokenizer.json27.9 MB0614fe83cadab421296e664e1f48f4261fa8fef6e03e63bb75c20f38e37d07d3
tokenizer_config.json4.20 KB9279e942392b742d633c7adbb89ebe002c98399db8926a7af5125c726f404070

Use it

$ fw get openai/gpt-oss-20b
# manifest sha256 0a3d3192b6cf… · 41.3 GB · 18 files
$ fw verify ./gpt-oss-20b openai/gpt-oss-20b
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/openai/gpt-oss-20b.json --dir ./gpt-oss-20b $ python3 fw.py verify ./gpt-oss-20b ./openai__gpt-oss-20b.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download openai/gpt-oss-20b --revision 6cee5e81ee83917806bbde320786a8fb61efebee --local-dir ./gpt-oss-20b
transformersLoad the weights in Python.
import os os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com" from transformers import AutoModelForCausalLM, AutoTokenizer tok = AutoTokenizer.from_pretrained("openai/gpt-oss-20b", revision="6cee5e81ee83917806bbde320786a8fb61efebee") model = AutoModelForCausalLM.from_pretrained("openai/gpt-oss-20b", revision="6cee5e81ee83917806bbde320786a8fb61efebee", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve openai/gpt-oss-20b --revision 6cee5e81ee83917806bbde320786a8fb61efebee
Run in Allternit Desktopcoming in Phase 1
Fine-tune in Freeweights Studiocoming in Phase 3

License

Name
Apache License 2.0
Id
Apache-2.0
Class
Permissive
Redistribution
yes
Text in
LICENSE
Text sha256
58d1e17ffe5109a7ae296caafcadfdbe6a7d176f0bc4ab01e12a689b0499d8bd
Terms gate
No extra terms beyond the license.

Read the license text

Licenses are checked against the license list. A custom license passes only after a recorded human audit.

Provenance

From: openai <huggingface.co/openai>Newsgroups: alt.freeweights.gpt-ossSubject: gpt-oss-20bDate: 2026-11-14Commit: 6cee5e8Signed: 2DC28CC7B26A283B ✓
Upstream
openai/gpt-oss-20b
Pinned commit
6cee5e81ee83917806bbde320786a8fb61efebee
Manifest
gpt-oss-20b.json · .minisig
Manifest sha256
0a3d3192b6cfd3071262d9a64e62f935a8d9b559f27ea7cdb6672caecf684979
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-14 06:31 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/openai/gpt-oss-20b.json $ curl -O https://freeweights.allternit.com/manifests/openai/gpt-oss-20b.json.minisig $ minisign -Vm gpt-oss-20b.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

Get it
Download
$ HF_ENDPOINT=https://freeweights.allternit.com hf download openai/gpt-oss-20b
Run in Allternit Desktopcoming in Phase 1
Signed manifest
minisign, key 2DC28CC7B26A283B. gpt-oss-20b.json. Provenance. Takedown history: none.
Source
huggingface.co/openai/gpt-oss-20b

Related models

All of alt.freeweights.gpt-oss →
From: openai <huggingface.co/openai>Subject: gpt-oss-120b
From: Comfy-Org <huggingface.co/Comfy-Org>Subject: YuE2
From: deepseek-ai <huggingface.co/deepseek-ai>Subject: DeepSeek-V4-Flash-0731
From: lmstudio-community <huggingface.co/lmstudio-community>Subject: DeepSeek-V4-Flash-0731-GGUF
From: HuggingFaceFW <huggingface.co/HuggingFaceFW>Subject: fineweb-edu
From: zai-org <huggingface.co/zai-org>Subject: GLM-4.7-Flash