alt.freeweights.abliterated / gemma-4-26B-A4B-it-heretic-msq-2.6bit

From:

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

gemma-4-26B-A4B-it-heretic-msq-2.6bit

Date: 2026-11-15Commit: 9c343e0Signed: 2DC28CC7B26A283B ✓

Image text to text model with 25.8B parameters. Safetensors weights, 10.2 GB in all. Published by mlx-community under Apache-2.0. Changed from the base model.

25.8B params

10.2GBgemma-4-26B-A4B-it-heretic-msq-2.6bitsafetensorspermissive

FactsParams25.8BSize10.2 GBFormatssafetensorsTaskimage text to textLicenseApache-2.0From sourcepermissive

$ fw get mlx-community/gemma-4-26B-A4B-it-heretic-msq-2.6bit
# manifest sha256 fa1e20f96449… · 10.2 GB · 13 files
$ fw verify ./gemma-4-26B-A4B-it-heretic-msq-2.6bit mlx-community/gemma-4-26B-A4B-it-heretic-msq-2.6bit

From sourceHosted (signed)mlx-community/gemma-4-26B-A4B-it-heretic-msq-2.6bitLast check: 2026-11-15 05:17 UTC

Run at home Get help

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

Quantized of gemma-4-26B-A4B-it.

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: 10.2 GB
Weights: 10.1 GB (safetensors)
Parameters: 25.8B
Formats: safetensors
Task: image text to text
License: Apache-2.0 (permissive)
Files: 13, 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 google/gemma-4-26B-A4B-it by the uploader. Read the model card at the source for the method and the layers touched.

Base model: google/gemma-4-26B-A4B-it

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 05:17 UTC	passed

Model card

From the publisher at commit 9c343e0. Shown as plain text with links; images open at the publisher.

gemma-4-26B-A4B-it-heretic — MLX 2.6 BPW#

Mixed-precision MLX quantization of coder3101/gemma-4-26B-A4B-it-heretic, 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: Vision (VLM)
Average: 2.6 bits per weight
Method: MLX Smart Quantize (MSQ)
AWQ scaling: applied to 30 groups

Evaluation#

Benchmark	Score	Samples
MMLU	70.2%	285
MMMLU	—	—
HellaSwag	82%	200
HellaSwag ML	—	—
GSM8K	90.9%	197
Tool Calls	74.2%	33

Files

13 files · 10.2 GBWeights 10.1 GB (safetensors). Sizes and sha256 from the signed manifest.

Hide all 13 files with their sha256

File	Size	sha256
.DS_Store	6.15 KB	d65165279105ca6773180500688df4bdc69a2c7b771752f0a46ef120b7fd8ec3
.gitattributes	1.57 KB	34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
.gitignore	18 B	70b90d3b85bf06ae5b403cf693ea32efadb3565dd01b15ab785decb97e0fa8b1
README.md	1.11 KB	bc728b113285c96d23eb780f0c94320959b61b2ef55c8acfd6f50f693c72a4d1
chat_template.jinja	17.5 KB	36e3a42e5cf14cd0020e72d92e1fdd9970f59b82170e421f0cbe1bb42bead3f0
config.json	66.7 KB	1a07a99df5ef3bfb55a38bf75917fe6de748808ab6b726d82418abec0957da54
generation_config.json	208 B	d4226bbe3117d2d253ba4609720ba82c6c4ce4627a9a6ae05387c78983ac03de
model-00001-of-00002.safetensors	5.36 GB	b0916ae984026cc26a693813a30e8f1042f3424d24f31ed26baeb5fa46290d02
model-00002-of-00002.safetensors	4.78 GB	70074cffc82e88cb2ff5ea7c506d449d094bdbc4c997f5cfe0467ac34b14ca54
model.safetensors.index.json	171 KB	15766bb640c3eeb2a96ba9ee4f3e3e0f465f745b0fce207bb31aed7276e52016
processor_config.json	902 B	1bd0d00776284f369c1eff5fb631e865dfcdca861e0b7d60dbef27fcf37436a8
tokenizer.json	32.2 MB	cc8d3a0ce36466ccc1278bf987df5f71db1719b9ca6b4118264f45cb627bfe0f
tokenizer_config.json	2.71 KB	a649af5e5f6c0b830dd2d65b25ef41e670ecb0431c711b0ab7bffa29756001b0

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

Upstream commit	Date	Contents
9c343e0cbf pinned now	2026-11-15 05:17 UTC	13 files · 10.2 GB

Use it

$ fw get mlx-community/gemma-4-26B-A4B-it-heretic-msq-2.6bit
# manifest sha256 fa1e20f96449… · 10.2 GB · 13 files
$ fw verify ./gemma-4-26B-A4B-it-heretic-msq-2.6bit mlx-community/gemma-4-26B-A4B-it-heretic-msq-2.6bit

fw.pyChecks the signature and every sha256, tries each source in order, resumes.

$ python3 fw.py get https://freeweights.allternit.com/manifests/mlx-community/gemma-4-26B-A4B-it-heretic-msq-2.6bit.json --dir ./gemma-4-26B-A4B-it-heretic-msq-2.6bit
$ python3 fw.py verify ./gemma-4-26B-A4B-it-heretic-msq-2.6bit ./mlx-community__gemma-4-26B-A4B-it-heretic-msq-2.6bit.json

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

$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/gemma-4-26B-A4B-it-heretic-msq-2.6bit --revision 9c343e0cbf958fcdbf2e174a0313b1c12e2344ab --local-dir ./gemma-4-26B-A4B-it-heretic-msq-2.6bit

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/gemma-4-26B-A4B-it-heretic-msq-2.6bit", revision="9c343e0cbf958fcdbf2e174a0313b1c12e2344ab")
model = AutoModelForImageTextToText.from_pretrained("mlx-community/gemma-4-26B-A4B-it-heretic-msq-2.6bit", revision="9c343e0cbf958fcdbf2e174a0313b1c12e2344ab", device_map="auto")

vLLMServe an OpenAI-compatible API.

$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve mlx-community/gemma-4-26B-A4B-it-heretic-msq-2.6bit --revision 9c343e0cbf958fcdbf2e174a0313b1c12e2344ab

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: bc728b113285c96d23eb780f0c94320959b61b2ef55c8acfd6f50f693c72a4d1
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: gemma-4-26B-A4B-it-heretic-msq-2.6bitDate: 2026-11-15Commit: 9c343e0Signed: 2DC28CC7B26A283B ✓

Upstream: mlx-community/gemma-4-26B-A4B-it-heretic-msq-2.6bit
Pinned commit: 9c343e0cbf958fcdbf2e174a0313b1c12e2344ab
Manifest: gemma-4-26B-A4B-it-heretic-msq-2.6bit.json · .minisig
Manifest sha256: fa1e20f9644959296071cdf8ad135f656634ad5cca80f12403e2d925c2e2d5b7
Signature: minisign, Ed25519, key 2DC28CC7B26A283B
Created: 2026-11-15 05:17 UTC
Generator: freeweights-manifest/0.1.0
Takedowns: None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/mlx-community/gemma-4-26B-A4B-it-heretic-msq-2.6bit.json
$ curl -O https://freeweights.allternit.com/manifests/mlx-community/gemma-4-26B-A4B-it-heretic-msq-2.6bit.json.minisig
$ minisign -Vm gemma-4-26B-A4B-it-heretic-msq-2.6bit.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

google/gemma-4-26B-A4B-it · 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/gemma-4-26B-A4B-it-heretic-msq-2.6bit

Open in Freeweights Studio

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

Signed manifest

minisign, key 2DC28CC7B26A283B. gemma-4-26B-A4B-it-heretic-msq-2.6bit.json. Provenance. Takedown history: none.

Source

huggingface.co/mlx-community/gemma-4-26B-A4B-it-heretic-msq-2.6bit

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

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

gemma-4-26B-A4B-it-heretic-msq-2.6bit

Works with

Runs with

Fine-tune with

Convert with

Evaluate with

Scan with

Works with

Overview

Model card

gemma-4-26B-A4B-it-heretic — MLX 2.6 BPW#

Details#

Evaluation#

Files

Use it

License

Provenance

How to verify

Model tree

Related models