alt.freeweights.abliterated / DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-OptiQ-4bit

From:

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

DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-OptiQ-4bit

Date: 2026-11-15Commit: 7e60c1fSigned: 2DC28CC7B26A283B ✓

Image text to text model with 9B parameters. Safetensors weights, 8.22 GB in all. Published by mlx-community under Apache-2.0. Changed from the base model.

9B params

8.22GBDeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-OptiQ-4bitsafetensorspermissive

FactsParams9BSize8.22 GBFormatssafetensorsTaskimage text to textLicenseApache-2.0From sourcepermissive

$ fw get mlx-community/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-OptiQ-4bit
# manifest sha256 6a6e6292b3cf… · 8.22 GB · 17 files
$ fw verify ./DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-OptiQ-4bit mlx-community/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-OptiQ-4bit

From sourceHosted (signed)mlx-community/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-OptiQ-4bitLast check: 2026-11-15 05:11 UTC

Run at home Get help

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

Quantized of DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic.

Works with

Run23 Fine-tune29 Convert15 Evaluate13 Scan13 Apps62

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 23

AIBrix fastllm ExLlamaV3

Transformers LocalAI tinygrad 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: 8.22 GB
Weights: 8.20 GB (safetensors)
Parameters: 9B
Formats: safetensors
Task: image text to text
License: Apache-2.0 (permissive)
Files: 17, each with a sha256
Publisher: mlx-community
Added: 2026-11-15
Section: alt.freeweights.abliterated

Lineage

Changed from the base model. The uploader's repo is named abliterated: refusal behavior was removed from xtools-at/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic by the uploader. Read the model card at the source for the method and the layers touched.

Base model: xtools-at/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic

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	2026-11-15 05:11 UTC	passed

Model card

From the publisher at commit 7e60c1f. Shown as plain text with links; images open at the publisher.

mlx-community/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-OptiQ-4bit#

Built with mlx-optiq, the MLX-native toolkit to quantize, fine-tune, and serve LLMs locally on Apple Silicon, no PyTorch and no cloud. All OptiQ quants · Docs

OptiQ mixed-precision quant of xtools-at/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic, an uncensored (heretic) version of a DeepSeek-V4-Pro reasoning distill into Qwen3.5-9B. It is a Qwen3.5-family vision-language model with a bundled MTP speculation head. 8.2 GB on disk.

What it is#

Property	Value
Base	xtools-at/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic (Qwen3.5, 9B)
Method	OptiQ mixed-precision, per-layer 4/8-bit
Bit allocation	Reused from the Qwen3.5-9B OptiQ recipe: the architecture is identical, so the per-layer sensitivity ranking transfers directly and no per-model sweep is needed
Layer split	116 components at 4-bit, 134 at 8-bit
Group size	64
On disk	8.2 GB
MTP	Speculation head preserved in `optiq/mtp.safetensors`
Vision	bf16 vision tower kept in `optiq_vision.safetensors` for image input
KV cache	Mixed-precision KV config in `kv_config.json`

Following the naming llama.cpp uses for its mixed quants, the "4bit" label denotes the family, not the weighted average.

Checked after conversion against the bf16 model on the same prompts (facts, arithmetic, code, explanation): the answers match.

Run it#

pip install mlx-optiq

import optiq  # registers the arch + MTP/vision sidecars
from mlx_lm import load, generate

model, tok = load("mlx-community/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-OptiQ-4bit")
prompt = tok.apply_chat_template(
    [{"role": "user", "content": "Explain mixed-precision quantization in two sentences."}],
    tokenize=False, add_generation_prompt=True,
)
print(generate(model, tok, prompt=prompt, max_tokens=400))

For image input plus an OpenAI- and Anthropic-compatible endpoint with mixed-precision KV cache:

optiq serve --model mlx-community/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-OptiQ-4bit

This is a reasoning model, so give it a generous token budget.

LM Studio: its downloader flattens the optiq/ folder. Move mtp.safetensors back into optiq/ or the speculation head is not found.

Links#

Project website: mlx-optiq.com
All OptiQ quants: mlx-optiq.com/models
Base model: xtools-at/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic

Files

17 files · 8.22 GBWeights 8.20 GB (safetensors). Sizes and sha256 from the signed manifest.

Hide all 17 files with their sha256

File	Size	sha256
.gitattributes	1.57 KB	34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
README.md	3.33 KB	48ae957c2a16cbe6098dcc202c19373de522705f5354644f2f2ce9c8ca6773c5
chat_template.jinja	8.74 KB	f7e41c826a3eea86dbd6ed2e204f0fc03262fcf720144e1dbb9b6d3e44e333a1
config.json	56.1 KB	375ab183111cd4b435e4bab9960b4a3ce13e7e4ebba3da358ace0fdee3947117
generation_config.json	142 B	e1a93f0711897bc19fae82c9a47b069669349061febf31fe4c444ea33071017b
kv_config.json	528 B	88b7f80fd9b3a202088f71889a7b43f818d63c4f836a60f26d5babe08093a10c
model-00001-of-00002.safetensors	5.35 GB	47ce669086111d9f33ed1168898b1b2f0d37b6a572ce275724768c3ed8804a32
model-00002-of-00002.safetensors	1.75 GB	2591892f16d9100d0ddff3d6c8901bd8927782873c91397a843033a5f7b2a4ae
model.safetensors.index.json	116 KB	93cf2b02e9220f4237d566044c2157c19b431559db2a16dfd427ba1f001e70e3
optiq/metadata.json	26.8 KB	84205ea08ea5d8ac906c98f72b9e3ecc42c2ac9086209c11616181e9b1818d90
optiq/mtp.safetensors	185 MB	1a9ad38b7c5a7a13befa7f2a77f1b63ac30f94a1861c4f0326f8ba69fc75d1b7
optiq_vision.safetensors	912 MB	f79255e0b1d6b5942ddb937edc52d436e279b99187cf289b23a468cbacfae58e
preprocessor_config.json	781 B	b99182e09450f26453502b3c3390cce36b33dc8c4a1f3ee21807762e168c74ab
processor_config.json	1.32 KB	3814737f2d4bfdd153a82364b3850f1be5dbc6f074a55c8d5fbf4d40127c3e87
tokenizer.json	20.0 MB	a5cd9732badce41de57e6efce8302930ded1c1188c5f81feb2bd6c24c4a1941f
tokenizer_config.json	1.57 KB	b09954254df1bd3e782d3c3865cad53b9f177e2f751bb07d2fc09e0b8f42b1f1
video_preprocessor_config.json	817 B	59c5c9eb52182eb14c06ffb10ca9effd29adce5f238a95de23ca14a38dbd2cb1

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

Upstream commit	Date	Contents
7e60c1f950 pinned now	2026-11-15 05:11 UTC	17 files · 8.22 GB

Use it

$ fw get mlx-community/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-OptiQ-4bit
# manifest sha256 6a6e6292b3cf… · 8.22 GB · 17 files
$ fw verify ./DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-OptiQ-4bit mlx-community/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-OptiQ-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/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-OptiQ-4bit.json --dir ./DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-OptiQ-4bit
$ python3 fw.py verify ./DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-OptiQ-4bit ./mlx-community__DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-OptiQ-4bit.json

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

$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-OptiQ-4bit --revision 7e60c1f95093252c7c0ca6d3c0e0160844c425c4 --local-dir ./DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-OptiQ-4bit

transformersLoad the weights in Python.

import os
os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com"
from transformers import AutoModelForImageTextToText, AutoProcessor
processor = AutoProcessor.from_pretrained("mlx-community/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-OptiQ-4bit", revision="7e60c1f95093252c7c0ca6d3c0e0160844c425c4")
model = AutoModelForImageTextToText.from_pretrained("mlx-community/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-OptiQ-4bit", revision="7e60c1f95093252c7c0ca6d3c0e0160844c425c4", device_map="auto")

vLLMServe an OpenAI-compatible API.

$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve mlx-community/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-OptiQ-4bit --revision 7e60c1f95093252c7c0ca6d3c0e0160844c425c4

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: 48ae957c2a16cbe6098dcc202c19373de522705f5354644f2f2ce9c8ca6773c5
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: DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-OptiQ-4bitDate: 2026-11-15Commit: 7e60c1fSigned: 2DC28CC7B26A283B ✓

Upstream: mlx-community/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-OptiQ-4bit
Pinned commit: 7e60c1f95093252c7c0ca6d3c0e0160844c425c4
Manifest: DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-OptiQ-4bit.json · .minisig
Manifest sha256: 6a6e6292b3cf56a960fa8e00cc1c0ea3b51a4098cd70d4583b0cb9c942d3bc91
Signature: minisign, Ed25519, key 2DC28CC7B26A283B
Created: 2026-11-15 05:11 UTC
Generator: freeweights-manifest/0.1.0
Takedowns: None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/mlx-community/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-OptiQ-4bit.json
$ curl -O https://freeweights.allternit.com/manifests/mlx-community/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-OptiQ-4bit.json.minisig
$ minisign -Vm DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-OptiQ-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

Parent

xtools-at/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic · 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/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-OptiQ-4bit

Open in Freeweights Studio

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

Signed manifest

minisign, key 2DC28CC7B26A283B. DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-OptiQ-4bit.json. Provenance. Takedown history: none.

Source

huggingface.co/mlx-community/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-OptiQ-4bit

Related models

All of alt.freeweights.abliterated →

From: xtools-at <huggingface.co/xtools-at>Subject: DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic

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

From:

mlx-community <huggingface.co/mlx-community>Subject: gemma-4-31B-it-uncensored-heretic-4bit

DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-OptiQ-4bit

Works with

Runs with

Fine-tune with

Convert with

Evaluate with

Scan with

Works with

Overview

Model card

mlx-community/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-OptiQ-4bit#

What it is#

Run it#

Links#

Files

Use it

License

Provenance

How to verify

Model tree

Related models