From: <huggingface.co/mlx-community> Newsgroups: alt.freeweights.gpt-ossSubject: gpt-oss-20b-mxfp4-bf16 Date: 2026-11-15Commit: f8c03dcSigned: 2DC28CC7B26A283B ✓ Text generation model with 20.9B parameters. Safetensors weights, 13.8 GB in all. Published by mlx-community under Apache-2.0.
20.9B params 13.8 GB gpt-oss-20b-mxfp4-bf16 safetensors permissive Facts Params 20.9B Size 13.8 GB Formats safetensors Task text generation License Apache-2.0 permissive
fw
$ fw get mlx-community/gpt-oss-20b-mxfp4-bf16
# manifest sha256 e29175cb8eac… · 13.8 GB · 11 files
$ fw verify ./gpt-oss-20b-mxfp4-bf16 mlx-community/gpt-oss-20b-mxfp4-bf16Hosted (signed) mlx-community/gpt-oss-20b-mxfp4-bf16 Last check: 2026-11-15 05:16 UTC
Get help: custom fine-tune or private deploy. We review your setup before we quote.
Quantized of gpt-oss-20b .
Works with
Runs with Ranked by fit to this model (safetensors), then by GitHub stars.
Show all 24 Fine-tune with Show all 29
Overview
Size 13.8 GB
Weights 13.8 GB (safetensors)
Parameters 20.9B
Formats safetensors
Task text generation
License Apache-2.0 (permissive)
Files 11, each with a sha256
Publisher mlx-community
Added 2026-11-15
Section alt.freeweights.gpt-oss Lineage
Original release from the publisher.
Base model: openai/gpt-oss-20b
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 huggingface.co 2026-11-15 05:16 UTC passed
Model card From the publisher at commit
f8c03dc . Shown as plain text with links; images open at the publisher.
This model mlx-community/gpt-oss-20b-mxfp4-bf16 was converted to MLX format from openai/gpt-oss-20b using mlx-lm version 0.31.3 .
Use with mlx#
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/gpt-oss-20b-mxfp4-bf16")
prompt = "hello"
if tokenizer.chat_template is not None:
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
messages, add_generation_prompt=True, return_dict=False,
)
response = generate(model, tokenizer, prompt=prompt, verbose=True) Files 11 files · 13.8 GB Weights 13.8 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 11 files with their sha256 File Size sha256 .gitattributes 1.57 KB 34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930 README.md 866 B f7f41f6f53d2295726cc1613cf56e6ff7fce5fff2b00777dc604817306e620b1 chat_template.jinja 16.7 KB a4c9919cbbd4acdd51ccffe22da049264b1b73e59055fa58811a99efbd7c8146 config.json 2.04 KB c9b23dd48c7aa043f0d241e4891f9f53f04348d3b673106b128e83b469ad1bcb generation_config.json 177 B f9970ada892d2d1f72e3ed0a6535ccebadd11897318794ca671d8c7014c957da model-00001-of-00003.safetensors 5.31 GB 0cdf187b97f05251d3586c1ef87678aa958151ae1ff6df345076b3bb8ec6246a model-00002-of-00003.safetensors 5.25 GB 811fe818f404071ab063073f27891bd380f3a3110dea6111b1900c1cba23ed9f model-00003-of-00003.safetensors 3.21 GB 4e889b7266f1df2d946e56841caabb5d1886c5503d3bc7084a24f2628e691f9e model.safetensors.index.json 46.3 KB 9c2386495d2a4f9fad3bef2b5cdaaec3ab7ee17e5087b338759865545e57f60a tokenizer.json 27.9 MB 0614fe83cadab421296e664e1f48f4261fa8fef6e03e63bb75c20f38e37d07d3 tokenizer_config.json 351 B e8bd3a5467e803377983a664138bf28bc3c9bf5c8134b57202d6ec22fa627cbf
Versions Each time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commit Date Contents f8c03dc936 pinned now 2026-11-15 05:16 UTC 11 files · 13.8 GB
Use it fw
$ fw get mlx-community/gpt-oss-20b-mxfp4-bf16
# manifest sha256 e29175cb8eac… · 13.8 GB · 11 files
$ fw verify ./gpt-oss-20b-mxfp4-bf16 mlx-community/gpt-oss-20b-mxfp4-bf16fw.py Checks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/mlx-community/gpt-oss-20b-mxfp4-bf16.json --dir ./gpt-oss-20b-mxfp4-bf16
$ python3 fw.py verify ./gpt-oss-20b-mxfp4-bf16 ./mlx-community__gpt-oss-20b-mxfp4-bf16.jsonhf The Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT =https://freeweights.allternit.com hf download mlx-community/gpt-oss-20b-mxfp4-bf16 --revision f8c03dc936dbf66db17d3411a177f498fcdd9a87 --local-dir ./gpt-oss-20b-mxfp4-bf16transformers Load 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-20b-mxfp4-bf16", revision="f8c03dc936dbf66db17d3411a177f498fcdd9a87")
model = AutoModelForCausalLM.from_pretrained("mlx-community/gpt-oss-20b-mxfp4-bf16", revision="f8c03dc936dbf66db17d3411a177f498fcdd9a87", device_map="auto")vLLM Serve an OpenAI-compatible API.
$ HF_ENDPOINT =https://freeweights.allternit.com vllm serve mlx-community/gpt-oss-20b-mxfp4-bf16 --revision f8c03dc936dbf66db17d3411a177f498fcdd9a87License 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 f7f41f6f53d2295726cc1613cf56e6ff7fce5fff2b00777dc604817306e620b1 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: <huggingface.co/mlx-community> Newsgroups: alt.freeweights.gpt-ossSubject: gpt-oss-20b-mxfp4-bf16 Date: 2026-11-15Commit: f8c03dcSigned: 2DC28CC7B26A283B ✓ How to verify
$ curl -O https://freeweights.allternit.com/manifests/mlx-community/gpt-oss-20b-mxfp4-bf16.json
$ curl -O https://freeweights.allternit.com/manifests/mlx-community/gpt-oss-20b-mxfp4-bf16.json.minisig
$ minisign -Vm gpt-oss-20b-mxfp4-bf16.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 model in the catalog names this one as its parent.
Get it
$ HF_ENDPOINT =https://freeweights.allternit.com hf download mlx-community/gpt-oss-20b-mxfp4-bf16Open in Freeweights Studio Pull, verify and run it in the Allternit app on Desktop, web or phone.
116.8B params 131 GB gpt-oss-120b safetensors permissive Facts Params 116.8B Size 131 GB Formats safetensors Task text generation License Apache-2.0 permissive flip From: <huggingface.co/unsloth> Subject: gpt-oss-120b 116.8B params 65.8 GB gpt-oss-120b-4bit safetensors permissive Facts Params 116.8B Size 65.8 GB Formats safetensors Task text generation License Apache-2.0 permissive flip From: <huggingface.co/mlx-community> Subject: gpt-oss-120b-4bit 116.8B params 234 GB gpt-oss-120b-BF16 safetensors permissive Facts Params 116.8B Size 234 GB Formats safetensors Task text generation License Apache-2.0 permissive flip From: <huggingface.co/unsloth> Subject: gpt-oss-120b-BF16 gpt-oss 63.4 GB gpt-oss-120b-GGUF gguf permissive Facts Params not stated Size 63.4 GB Formats gguf Task not tagged License Apache-2.0 permissive flip From: <huggingface.co/lmstudio-community> Subject: gpt-oss-120b-GGUF gpt-oss 1.01 TB gpt-oss-120b-GGUF gguf permissive Facts Params not stated Size 1.01 TB Formats gguf Task text generation License Apache-2.0 permissive flip From: <huggingface.co/unsloth> Subject: gpt-oss-120b-GGUF 116.8B params 124 GB gpt-oss-120b-MLX-8bit safetensors permissive Facts Params 116.8B Size 124 GB Formats safetensors Task text generation License Apache-2.0 permissive flip From: <huggingface.co/lmstudio-community> Subject: gpt-oss-120b-MLX-8bit
mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.gpt-ossSubject: 
unsloth 
lmstudio-community