alt.freeweights.abliterated / gemma-4-E4B-it-OBLITERATED-mlx-8Bit

From:

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

gemma-4-E4B-it-OBLITERATED-mlx-8Bit

Date: 2026-11-15Commit: db71b26Signed: 2DC28CC7B26A283B ✓

Text generation model with 7.5B parameters. Safetensors weights, 8.02 GB in all. Published by mlx-community under Apache-2.0. Changed from the base model.

7.5B params

8.02GBgemma-4-E4B-it-OBLITERATED-mlx-8Bitsafetensorspermissive

FactsParams7.5BSize8.02 GBFormatssafetensorsTasktext generationLicenseApache-2.0From sourcepermissive

$ fw get mlx-community/gemma-4-E4B-it-OBLITERATED-mlx-8Bit
# manifest sha256 53cb33335317… · 8.02 GB · 10 files
$ fw verify ./gemma-4-E4B-it-OBLITERATED-mlx-8Bit mlx-community/gemma-4-E4B-it-OBLITERATED-mlx-8Bit

From sourceHosted (signed)mlx-community/gemma-4-E4B-it-OBLITERATED-mlx-8BitLast check: 2026-11-15 04:55 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-E4B-it-OBLITERATED.

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: 8.02 GB
Weights: 7.99 GB (safetensors)
Parameters: 7.5B
Formats: safetensors
Task: text generation
License: Apache-2.0 (permissive)
Files: 10, 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 OBLITERATUS/gemma-4-E4B-it-OBLITERATED by the uploader. Read the model card at the source for the method and the layers touched.

Base model: OBLITERATUS/gemma-4-E4B-it-OBLITERATED

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 04:55 UTC	passed

Model card

From the publisher at commit db71b26. Shown as plain text with links; images open at the publisher.

mlx-community/gemma-4-E4B-it-OBLITERATED-mlx-8Bit#

The Model mlx-community/gemma-4-E4B-it-OBLITERATED-mlx-8Bit was converted to MLX format from OBLITERATUS/gemma-4-E4B-it-OBLITERATED (v3) using mlx-lm version 0.31.2.

Use with mlx#

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/gemma-4-E4B-it-OBLITERATED-mlx-8Bit")

prompt="hello"

if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)

Files

10 files · 8.02 GBWeights 7.99 GB (safetensors). Sizes and sha256 from the signed manifest.

Hide all 10 files with their sha256

File	Size	sha256
.gitattributes	1.57 KB	34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
README.md	1.10 KB	98618d6d5073e27f0874ac18d7e9ecd9cc3f4b239fac95e18e710562b7eed2b3
chat_template.jinja	17.3 KB	2f1b4d75d067bae3fe44e676721c7f077d243bc007156cb9c2f8b5836613d082
config.json	4.96 KB	5dda742021a5f1039af189cf311b65fb02bdf2b22d5be2ff1fa056c17c9a2ba8
generation_config.json	203 B	5c146fd069b88099b6e41eadf79fdcd37908cfa6078594ca2bac4603052965d6
model-00001-of-00002.safetensors	4.96 GB	6a4597fc05c8ea3ff4864db8f3c2382c7ccc63ff43f0b8a59f6a89110d5fb27a
model-00002-of-00002.safetensors	3.02 GB	6605727354a294bad9e1c99ea51697698261a1d068d52c1e07a4b7058af6feab
model.safetensors.index.json	151 KB	d1e0945a6e61e633966f3cccfbabf7b2d8c3839239501be3cf25840b61c375ea
tokenizer.json	32.2 MB	cc8d3a0ce36466ccc1278bf987df5f71db1719b9ca6b4118264f45cb627bfe0f
tokenizer_config.json	2.91 KB	3867bdb57a8c90ec9c65e97e7845d29f8e89aa81743628254e52a0752fd9b590

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

Upstream commit	Date	Contents
db71b26442 pinned now	2026-11-15 04:55 UTC	10 files · 8.02 GB

Use it

$ fw get mlx-community/gemma-4-E4B-it-OBLITERATED-mlx-8Bit
# manifest sha256 53cb33335317… · 8.02 GB · 10 files
$ fw verify ./gemma-4-E4B-it-OBLITERATED-mlx-8Bit mlx-community/gemma-4-E4B-it-OBLITERATED-mlx-8Bit

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-E4B-it-OBLITERATED-mlx-8Bit.json --dir ./gemma-4-E4B-it-OBLITERATED-mlx-8Bit
$ python3 fw.py verify ./gemma-4-E4B-it-OBLITERATED-mlx-8Bit ./mlx-community__gemma-4-E4B-it-OBLITERATED-mlx-8Bit.json

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

$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/gemma-4-E4B-it-OBLITERATED-mlx-8Bit --revision db71b2644248b4f9e7e31ede5e6f631b870d8af5 --local-dir ./gemma-4-E4B-it-OBLITERATED-mlx-8Bit

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/gemma-4-E4B-it-OBLITERATED-mlx-8Bit", revision="db71b2644248b4f9e7e31ede5e6f631b870d8af5")
model = AutoModelForCausalLM.from_pretrained("mlx-community/gemma-4-E4B-it-OBLITERATED-mlx-8Bit", revision="db71b2644248b4f9e7e31ede5e6f631b870d8af5", device_map="auto")

vLLMServe an OpenAI-compatible API.

$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve mlx-community/gemma-4-E4B-it-OBLITERATED-mlx-8Bit --revision db71b2644248b4f9e7e31ede5e6f631b870d8af5

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: 98618d6d5073e27f0874ac18d7e9ecd9cc3f4b239fac95e18e710562b7eed2b3
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-E4B-it-OBLITERATED-mlx-8BitDate: 2026-11-15Commit: db71b26Signed: 2DC28CC7B26A283B ✓

Upstream: mlx-community/gemma-4-E4B-it-OBLITERATED-mlx-8Bit
Pinned commit: db71b2644248b4f9e7e31ede5e6f631b870d8af5
Manifest: gemma-4-E4B-it-OBLITERATED-mlx-8Bit.json · .minisig
Manifest sha256: 53cb33335317377516219d26adc188dfa982d4f052b9021222c96a59d40f76b1
Signature: minisign, Ed25519, key 2DC28CC7B26A283B
Created: 2026-11-15 04:55 UTC
Generator: freeweights-manifest/0.1.0
Takedowns: None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/mlx-community/gemma-4-E4B-it-OBLITERATED-mlx-8Bit.json
$ curl -O https://freeweights.allternit.com/manifests/mlx-community/gemma-4-E4B-it-OBLITERATED-mlx-8Bit.json.minisig
$ minisign -Vm gemma-4-E4B-it-OBLITERATED-mlx-8Bit.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

OBLITERATUS/gemma-4-E4B-it-OBLITERATED · 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-E4B-it-OBLITERATED-mlx-8Bit

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-E4B-it-OBLITERATED-mlx-8Bit.json. Provenance. Takedown history: none.

Source

huggingface.co/mlx-community/gemma-4-E4B-it-OBLITERATED-mlx-8Bit

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:

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

gemma-4-E4B-it-OBLITERATED-mlx-8Bit

Works with

Runs with

Fine-tune with

Convert with

Evaluate with

Scan with

Works with

Overview

Model card

mlx-community/gemma-4-E4B-it-OBLITERATED-mlx-8Bit#

Use with mlx#

Files

Use it

License

Provenance

How to verify

Model tree

Related models