alt.freeweights.abliterated / RavenX-CyberAgent-Qwen3.6-35B-A3B-Opus-4.7-OpenMythos-Pentester-BugHunter-RATH-mlx-4bit-msq
From: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.abliteratedSubject:

RavenX-CyberAgent-Qwen3.6-35B-A3B-Opus-4.7-OpenMythos-Pentester-BugHunter-RATH-mlx-4bit-msq

Date: 2026-11-15Commit: d519e9aSigned: 2DC28CC7B26A283B ✓

Text generation model with 34.7B parameters. Safetensors weights, 21.7 GB in all. Published by mlx-community under Apache-2.0. Changed from the base model.

34.7B params21.7GBRavenX-CyberAgent-Qwen3.6-35B-A3B-Opus-4.7-OpenMythos-Pentester-BugHunter-RATH-mlx-4bit-msqsafetensorspermissive
FactsParams34.7BSize21.7 GBFormatssafetensorsTasktext generationLicenseApache-2.0From sourcepermissive
$ fw get mlx-community/RavenX-CyberAgent-Qwen3.6-35B-A3B-Opus-4.7-OpenMythos-Pentester-BugHunter-RATH-mlx-4bit-msq
# manifest sha256 80ebcee8f685… · 21.7 GB · 14 files
$ fw verify ./RavenX-CyberAgent-Qwen3.6-35B-A3B-Opus-4.7-OpenMythos-Pentester-BugHunter-RATH-mlx-4bit-msq mlx-community/RavenX-CyberAgent-Qwen3.6-35B-A3B-Opus-4.7-OpenMythos-Pentester-BugHunter-RATH-mlx-4bit-msq
From sourceHosted (signed)mlx-community/RavenX-CyberAgent-Qwen3.6-35B-A3B-Opus-4.7-OpenMythos-Pentester-BugHunter-RATH-mlx-4bit-msqLast check: 2026-11-15 05:18 UTC

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

Quantized of Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated.

Works with

Overview

Size
21.7 GB
Weights
21.7 GB (safetensors)
Parameters
34.7B
Formats
safetensors
Task
text generation
License
Apache-2.0 (permissive)
Files
14, each with a sha256
Publisher
mlx-community
Added
2026-11-15
Section
alt.freeweights.abliterated
Lineage

Changed from the base model. A repackaged copy (same weights, other format) of huihui-ai/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated, which is abliterated: its refusal behavior was removed by its uploader. Read the model card at the source for the method.

Base model: huihui-ai/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated

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 05:18 UTCpassed

Model card

From the publisher at commit d519e9a. Shown as plain text with links; images open at the publisher.

RavenX-CyberAgent-Qwen3.6-35B-A3B-Opus-4.7-OpenMythos-Pentester-BugHunter-RATH-mlx — MLX 4.5 BPW#

Mixed-precision MLX quantization of deadbydawn101/RavenX-CyberAgent-Qwen3.6-35B-A3B-Opus-4.7-OpenMythos-Pentester-BugHunter-RATH-mlx, quantized with MLX Smart Quantize (MSQ) — my own sensitivity-based mixed-precision quantization method for Apple Silicon. It measures per-layer NMSE and assigns optimal bit widths automatically, combining architecture knowledge with measured data.

Details#

  • Type: Text (LLM)
  • Average: 4.50 bits per weight
  • Method: MLX Smart Quantize (MSQ)
  • AWQ scaling: applied to 50 groups

Files

14 files · 21.7 GBWeights 21.7 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 14 files with their sha256
FileSizesha256
.gitattributes1.57 KB34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
.gitignore18 B70b90d3b85bf06ae5b403cf693ea32efadb3565dd01b15ab785decb97e0fa8b1
README.md1.30 KB47d6ad46c70c7e64e5673e1b02ec29ae8b91723c5e1dc6b7917c9b5a6356656a
chat_template.jinja8.06 KB55d4931433fe502b794226ee7f4d206a6bdd436ac9f80eb7d8ebb4c639f9ea0c
config.json80.7 KB185ebbf95ae3edaa4eac288378fe075f88d7e61af3b08b97e8fd36b20f286885
model-00001-of-00005.safetensors5.20 GBe227d23ee7d87740e684f8231869e2cd658f8c2bd803c9a5cc9e9ba89fe9212e
model-00002-of-00005.safetensors5.33 GB14dc88fc6d5ed83ba85f592c5acd354d6f675c1fcf5c78563f07816d2e413370
model-00003-of-00005.safetensors5.30 GB1e37e46c0279891ed010fe1ee79893cebd7c7f0e99ff9e7502d655b39299b1ea
model-00004-of-00005.safetensors5.30 GBc8d98e609998ffc753135ef241c9cd43f544f7e346e9cb83882934baa5395886
model-00005-of-00005.safetensors540 MB145818a7e8f32071c56f6f817aa452aff235745f82033f141f07f5f6f7bc41c6
model.safetensors.index.json171 KB8ee827a7df9a7a5b3efa63eda666d5626da83fb6275e3048897944d429a73ff1
quant_recipe.json625 Bd1a2697299eb8ee9af2c525637a4132bcb99301836575a31d3365431539bbfc2
tokenizer.json20.0 MB87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
tokenizer_config.json1.23 KB4fee3510060b62fa444b0e3586cdf000fad17900270e7d666b91a58e9b40fcfe
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
d519e9ac91 pinned now2026-11-15 05:18 UTC14 files · 21.7 GB

Use it

$ fw get mlx-community/RavenX-CyberAgent-Qwen3.6-35B-A3B-Opus-4.7-OpenMythos-Pentester-BugHunter-RATH-mlx-4bit-msq
# manifest sha256 80ebcee8f685… · 21.7 GB · 14 files
$ fw verify ./RavenX-CyberAgent-Qwen3.6-35B-A3B-Opus-4.7-OpenMythos-Pentester-BugHunter-RATH-mlx-4bit-msq mlx-community/RavenX-CyberAgent-Qwen3.6-35B-A3B-Opus-4.7-OpenMythos-Pentester-BugHunter-RATH-mlx-4bit-msq
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/mlx-community/RavenX-CyberAgent-Qwen3.6-35B-A3B-Opus-4.7-OpenMythos-Pentester-BugHunter-RATH-mlx-4bit-msq.json --dir ./RavenX-CyberAgent-Qwen3.6-35B-A3B-Opus-4.7-OpenMythos-Pentester-BugHunter-RATH-mlx-4bit-msq $ python3 fw.py verify ./RavenX-CyberAgent-Qwen3.6-35B-A3B-Opus-4.7-OpenMythos-Pentester-BugHunter-RATH-mlx-4bit-msq ./mlx-community__RavenX-CyberAgent-Qwen3.6-35B-A3B-Opus-4.7-OpenMythos-Pentester-BugHunter-RATH-mlx-4bit-msq.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/RavenX-CyberAgent-Qwen3.6-35B-A3B-Opus-4.7-OpenMythos-Pentester-BugHunter-RATH-mlx-4bit-msq --revision d519e9ac91affcdc40861ccaef4d9cee1f8c826e --local-dir ./RavenX-CyberAgent-Qwen3.6-35B-A3B-Opus-4.7-OpenMythos-Pentester-BugHunter-RATH-mlx-4bit-msq
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/RavenX-CyberAgent-Qwen3.6-35B-A3B-Opus-4.7-OpenMythos-Pentester-BugHunter-RATH-mlx-4bit-msq", revision="d519e9ac91affcdc40861ccaef4d9cee1f8c826e") model = AutoModelForCausalLM.from_pretrained("mlx-community/RavenX-CyberAgent-Qwen3.6-35B-A3B-Opus-4.7-OpenMythos-Pentester-BugHunter-RATH-mlx-4bit-msq", revision="d519e9ac91affcdc40861ccaef4d9cee1f8c826e", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve mlx-community/RavenX-CyberAgent-Qwen3.6-35B-A3B-Opus-4.7-OpenMythos-Pentester-BugHunter-RATH-mlx-4bit-msq --revision d519e9ac91affcdc40861ccaef4d9cee1f8c826e

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
47d6ad46c70c7e64e5673e1b02ec29ae8b91723c5e1dc6b7917c9b5a6356656a
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.abliteratedSubject: RavenX-CyberAgent-Qwen3.6-35B-A3B-Opus-4.7-OpenMythos-Pentester-BugHunter-RATH-mlx-4bit-msqDate: 2026-11-15Commit: d519e9aSigned: 2DC28CC7B26A283B ✓
Upstream
mlx-community/RavenX-CyberAgent-Qwen3.6-35B-A3B-Opus-4.7-OpenMythos-Pentester-BugHunter-RATH-mlx-4bit-msq
Pinned commit
d519e9ac91affcdc40861ccaef4d9cee1f8c826e
Manifest
RavenX-CyberAgent-Qwen3.6-35B-A3B-Opus-4.7-OpenMythos-Pentester-BugHunter-RATH-mlx-4bit-msq.json · .minisig
Manifest sha256
80ebcee8f6851f02e52a42c98c88f2c8577d2d7828b85c42870cba7444d1996d
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 05:18 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/mlx-community/RavenX-CyberAgent-Qwen3.6-35B-A3B-Opus-4.7-OpenMythos-Pentester-BugHunter-RATH-mlx-4bit-msq.json $ curl -O https://freeweights.allternit.com/manifests/mlx-community/RavenX-CyberAgent-Qwen3.6-35B-A3B-Opus-4.7-OpenMythos-Pentester-BugHunter-RATH-mlx-4bit-msq.json.minisig $ minisign -Vm RavenX-CyberAgent-Qwen3.6-35B-A3B-Opus-4.7-OpenMythos-Pentester-BugHunter-RATH-mlx-4bit-msq.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

huihui-ai/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated · 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/RavenX-CyberAgent-Qwen3.6-35B-A3B-Opus-4.7-OpenMythos-Pentester-BugHunter-RATH-mlx-4bit-msq
Open in Freeweights Studio

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

Signed manifest
From: xtools-at <huggingface.co/xtools-at>Subject: DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic
From: mlx-community <huggingface.co/mlx-community>Subject: DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-OptiQ-4bit
From: mlx-community <huggingface.co/mlx-community>Subject: gemma-4-26B-A4B-it-heretic-msq-2.6bit
From: coder3101 <huggingface.co/coder3101>Subject: gemma-4-31B-it-heretic
From: Ilya626 <huggingface.co/Ilya626>Subject: gemma-4-31B-it-SDFT-Heretic-RP
From: llmfan46 <huggingface.co/llmfan46>Subject: gemma-4-31B-it-uncensored-heretic