alt.freeweights.gpt-oss / gpt-oss-20b-MXFP4-Q8

From:

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

gpt-oss-20b-MXFP4-Q8

Date: 2026-11-14Commit: 773a7daSigned: 2DC28CC7B26A283B ✓

Text generation model with 20.9B parameters. Safetensors weights, 12.1 GB in all. Published by mlx-community under Apache-2.0.

20.9B params

12.1GBgpt-oss-20b-MXFP4-Q8safetensorspermissive

FactsParams20.9BSize12.1 GBFormatssafetensorsTasktext generationLicenseApache-2.0From sourcepermissive

$ fw get mlx-community/gpt-oss-20b-MXFP4-Q8
# manifest sha256 b1af73062c13… · 12.1 GB · 12 files
$ fw verify ./gpt-oss-20b-MXFP4-Q8 mlx-community/gpt-oss-20b-MXFP4-Q8

From sourceHosted (signed)mlx-community/gpt-oss-20b-MXFP4-Q8Last check: 2026-11-14 21:30 UTC

Run at home Get help

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

Quantized of gpt-oss-20b.

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: 12.1 GB
Weights: 12.1 GB (safetensors)
Parameters: 20.9B
Formats: safetensors
Task: text generation
License: Apache-2.0 (permissive)
Files: 12, each with a sha256
Publisher: mlx-community
Added: 2026-11-14
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
From source	huggingface.co	2026-11-14 21:30 UTC	passed

Model card

From the publisher at commit 773a7da. Shown as plain text with links; images open at the publisher.

mlx-community/gpt-oss-20b-MXFP4-Q8#

This model mlx-community/gpt-oss-20b-MXFP4-Q8 was converted to MLX format from openai/gpt-oss-20b using mlx-lm version 0.27.0.

Use with mlx#

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/gpt-oss-20b-MXFP4-Q8")

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

12 files · 12.1 GBWeights 12.1 GB (safetensors). Sizes and sha256 from the signed manifest.

Hide all 12 files with their sha256

File	Size	sha256
.gitattributes	1.57 KB	34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
README.md	838 B	a78be99ae980283461597ded48982280aa6aee2f250ba3c05ad9aeebe95e7974
chat_template.jinja	16.7 KB	a4c9919cbbd4acdd51ccffe22da049264b1b73e59055fa58811a99efbd7c8146
config.json	34.0 KB	d1c1f73bf62116ed0bb37c068af80534543cd1de9b61d609fc01bf70920e842d
generation_config.json	177 B	f9970ada892d2d1f72e3ed0a6535ccebadd11897318794ca671d8c7014c957da
model-00001-of-00003.safetensors	5.30 GB	57f4846924652b1b23537c6c6d6b65f64fde811e47369d4e23c5c45b4d7584a7
model-00002-of-00003.safetensors	5.28 GB	4a862a873080e489db16125877e19553b958562ff4dd0246135bc061c3293652
model-00003-of-00003.safetensors	1.49 GB	16c32bb8dbd1fa8d556815706589d6d6480d29946196cd2fe2b721d4daf84132
model.safetensors.index.json	67.0 KB	6fa724aa7a9130561f9b97debcc06c56ba150d8fbd58fc1168f53a22d6a5490a
special_tokens_map.json	440 B	8464cabd6eda239fe46ebf8ae63b46c417721784a961a022f6b59174a2cda0e2
tokenizer.json	27.9 MB	0614fe83cadab421296e664e1f48f4261fa8fef6e03e63bb75c20f38e37d07d3
tokenizer_config.json	21.7 KB	2d8386578f85ea1fa698e78c58b2d8503e8122d6b110b61f93d3995601b07d91

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

Upstream commit	Date	Contents
773a7da77e pinned now manifest updated, same commit	2026-11-14 21:30 UTC	12 files · 12.1 GB
773a7da77e	2026-11-14 21:30 UTC	12 files · 12.1 GB

Use it

$ fw get mlx-community/gpt-oss-20b-MXFP4-Q8
# manifest sha256 b1af73062c13… · 12.1 GB · 12 files
$ fw verify ./gpt-oss-20b-MXFP4-Q8 mlx-community/gpt-oss-20b-MXFP4-Q8

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-20b-MXFP4-Q8.json --dir ./gpt-oss-20b-MXFP4-Q8
$ python3 fw.py verify ./gpt-oss-20b-MXFP4-Q8 ./mlx-community__gpt-oss-20b-MXFP4-Q8.json

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

$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/gpt-oss-20b-MXFP4-Q8 --revision 773a7da77e569019bb0fd17a554b263738d669a3 --local-dir ./gpt-oss-20b-MXFP4-Q8

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-20b-MXFP4-Q8", revision="773a7da77e569019bb0fd17a554b263738d669a3")
model = AutoModelForCausalLM.from_pretrained("mlx-community/gpt-oss-20b-MXFP4-Q8", revision="773a7da77e569019bb0fd17a554b263738d669a3", device_map="auto")

vLLMServe an OpenAI-compatible API.

$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve mlx-community/gpt-oss-20b-MXFP4-Q8 --revision 773a7da77e569019bb0fd17a554b263738d669a3

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. 2026-11-14
Text in: README.md
Text sha256: a78be99ae980283461597ded48982280aa6aee2f250ba3c05ad9aeebe95e7974
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-20b-MXFP4-Q8Date: 2026-11-14Commit: 773a7daSigned: 2DC28CC7B26A283B ✓

Upstream: mlx-community/gpt-oss-20b-MXFP4-Q8
Pinned commit: 773a7da77e569019bb0fd17a554b263738d669a3
Manifest: gpt-oss-20b-MXFP4-Q8.json · .minisig
Manifest sha256: b1af73062c138d3844641964f0732c67a6fe7856877536b2774a837b44fad763
Signature: minisign, Ed25519, key 2DC28CC7B26A283B
Created: 2026-11-14 21:30 UTC
Generator: freeweights-manifest/0.1.0
Takedowns: None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/mlx-community/gpt-oss-20b-MXFP4-Q8.json
$ curl -O https://freeweights.allternit.com/manifests/mlx-community/gpt-oss-20b-MXFP4-Q8.json.minisig
$ minisign -Vm gpt-oss-20b-MXFP4-Q8.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

openai/gpt-oss-20b · 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/gpt-oss-20b-MXFP4-Q8

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-20b-MXFP4-Q8.json. Provenance. Takedown history: none.

Source

huggingface.co/mlx-community/gpt-oss-20b-MXFP4-Q8

Related models

All of alt.freeweights.gpt-oss →

From:

unsloth <huggingface.co/unsloth>Subject: gpt-oss-120b

From:

mlx-community <huggingface.co/mlx-community>Subject: gpt-oss-120b-4bit

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

gpt-oss-20b-MXFP4-Q8

Works with

Runs with

Fine-tune with

Convert with

Evaluate with

Scan with

Works with

Overview

Model card

mlx-community/gpt-oss-20b-MXFP4-Q8#

Use with mlx#

Files

Use it

License

Provenance

How to verify

Model tree

Related models