alt.freeweights.abliterated / GLM-5.3-Flash-abliterated-Maya-M-GGUF
From: alesha-pro <huggingface.co/alesha-pro>Newsgroups: alt.freeweights.abliteratedSubject:

GLM-5.3-Flash-abliterated-Maya-M-GGUF

Date: 2026-11-14Commit: 3518a2dSigned: 2DC28CC7B26A283B ✓

Image text to text model. Gguf weights, 117 GB in all. Published by alesha-pro under MIT. Changed from the base model.

abliterated117GBGLM-5.3-Flash-abliterated-Maya-M-GGUFggufpermissive
FactsParamsnot statedSize117 GBFormatsggufTaskimage text to textLicenseMITFrom sourcepermissive
$ fw get alesha-pro/GLM-5.3-Flash-abliterated-Maya-M-GGUF
# manifest sha256 a147733ab8a7… · 117 GB · 10 files
$ fw verify ./GLM-5.3-Flash-abliterated-Maya-M-GGUF alesha-pro/GLM-5.3-Flash-abliterated-Maya-M-GGUF
From sourcealesha-pro/GLM-5.3-Flash-abliterated-Maya-M-GGUFLast check: 2026-11-14 15:35 UTC

Overview

Size
117 GB
Weights
9.43 MB (smallest of 2 GGUF variants)
Parameters
not stated
Formats
gguf
Task
image text to text
License
MIT (permissive)
Files
10, each with a sha256
Publisher
alesha-pro
Added
2026-11-14
Section
alt.freeweights.abliterated
Lineage

Changed from the base model. Weights are Project Maya's Maya-M quant of GLM-5.3-Flash, unchanged. Adds a 2.2 MB vector (3 refusal directions per layer, layers 1 to 44) and a Maya engine patch that removes them at run time.

Base model: peasantsmith/GLM-5.3-Flash-Maya-GGUF

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.co2026-11-14 15:35 UTCpassed

Files

10 files · 117 GBWeights 9.43 MB (smallest of 2 GGUF variants). Sizes and sha256 from the signed manifest.
Hide all 10 files with their sha256
FileSizesha256
.gitattributes2.02 KBc969f8a5c3f6c54bca8a82ddadb43442e44b8e2ff4c896eda08f48b17e67edb2
LICENSE1.07 KB30b85b6b9659f2e78aa259f8faf5d920a68dee7c9ced3fa6dba1f19f2bc4fca1
Maya-M/GLM-5.3-Flash-Maya-M-IQ2_S-00001-of-00003.gguf47.7 GB3ac0f066ec45af3432d59b33de49bdfb29156432b627240b35769c7d02cc6c02
Maya-M/GLM-5.3-Flash-Maya-M-IQ2_S-00002-of-00003.gguf47.8 GB285951d2afa0cd98285b03d0dc4aa68d83daf1a6f4a2594fe40b0cdd27ade485
Maya-M/GLM-5.3-Flash-Maya-M-IQ2_S-00003-of-00003.gguf20.5 GBebf1ce713f71207747e10eeebed87597969d8b5e1d9dd817420d2c2f7ca51e0e
README.md7.11 KB2705c4c0915a765944342d00ddd465ddf16809c624eb0b100085922832901351
SHA256SUMS561 Bce77f50cc1e3dcb7e3a0baa66e06a2cd40c4923443aeb2c85da75b017493207e
vector/glm53-refusal-per-block-3dir.layers45.f322.21 MBb0debc326b06c956039fd75dc1cb759dd46c4aa5e868bbfef1a5b0607c3552b7
vision/GLM-5.3-Flash-vocab.gguf9.43 MB8f53cb1bd2e631c14ef413e3284735d9e53f3c508d07a6f609e705b487105912
vision/mmproj-GLM-5.3-Flash-F16.gguf1.13 GB3627575df16bd152db0f3fd7e488d270b33f3a9e6c7fa3b1b8ac381faafde882

Use it

$ fw get alesha-pro/GLM-5.3-Flash-abliterated-Maya-M-GGUF
# manifest sha256 a147733ab8a7… · 117 GB · 10 files
$ fw verify ./GLM-5.3-Flash-abliterated-Maya-M-GGUF alesha-pro/GLM-5.3-Flash-abliterated-Maya-M-GGUF
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/alesha-pro/GLM-5.3-Flash-abliterated-Maya-M-GGUF.json --dir ./GLM-5.3-Flash-abliterated-Maya-M-GGUF $ python3 fw.py verify ./GLM-5.3-Flash-abliterated-Maya-M-GGUF ./alesha-pro__GLM-5.3-Flash-abliterated-Maya-M-GGUF.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download alesha-pro/GLM-5.3-Flash-abliterated-Maya-M-GGUF --revision 3518a2d20e5a2ea8d9468718745dca5f72aed5f1 --local-dir ./GLM-5.3-Flash-abliterated-Maya-M-GGUF
llama.cppDownload one GGUF variant (vision, 9.43 MB), then serve it.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download alesha-pro/GLM-5.3-Flash-abliterated-Maya-M-GGUF --include "vision/*" --local-dir ./GLM-5.3-Flash-abliterated-Maya-M-GGUF $ llama-server -m ./GLM-5.3-Flash-abliterated-Maya-M-GGUF/vision/GLM-5.3-Flash-vocab.gguf
OllamaMake an Ollama model from the downloaded file.
$ printf 'FROM ./GLM-5.3-Flash-abliterated-Maya-M-GGUF/vision/GLM-5.3-Flash-vocab.gguf\n' > Modelfile $ ollama create glm-5.3-flash-abliterated-maya-m-gguf -f Modelfile
Run in Allternit Desktopcoming in Phase 1
Fine-tune in Freeweights Studiocoming in Phase 3

License

Name
MIT License
Id
MIT
Class
Permissive
Redistribution
yes
Text in
LICENSE
Text sha256
30b85b6b9659f2e78aa259f8faf5d920a68dee7c9ced3fa6dba1f19f2bc4fca1
Terms gate
No extra terms beyond the license.

Read the license text

Licenses are checked against the license list. A custom license passes only after a recorded human audit.

Provenance

From: alesha-pro <huggingface.co/alesha-pro>Newsgroups: alt.freeweights.abliteratedSubject: GLM-5.3-Flash-abliterated-Maya-M-GGUFDate: 2026-11-14Commit: 3518a2dSigned: 2DC28CC7B26A283B ✓
Upstream
alesha-pro/GLM-5.3-Flash-abliterated-Maya-M-GGUF
Pinned commit
3518a2d20e5a2ea8d9468718745dca5f72aed5f1
Manifest
GLM-5.3-Flash-abliterated-Maya-M-GGUF.json · .minisig
Manifest sha256
a147733ab8a7ae93fcfaf26c5d10d5a87f1d5f7baad15286e25ac333192dbabe
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-14 15:35 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/alesha-pro/GLM-5.3-Flash-abliterated-Maya-M-GGUF.json $ curl -O https://freeweights.allternit.com/manifests/alesha-pro/GLM-5.3-Flash-abliterated-Maya-M-GGUF.json.minisig $ minisign -Vm GLM-5.3-Flash-abliterated-Maya-M-GGUF.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

Get it
Download
$ HF_ENDPOINT=https://freeweights.allternit.com hf download alesha-pro/GLM-5.3-Flash-abliterated-Maya-M-GGUF
Run in Allternit Desktopcoming in Phase 1
Signed manifest
minisign, key 2DC28CC7B26A283B. GLM-5.3-Flash-abliterated-Maya-M-GGUF.json. Provenance. Takedown history: none.
From: huihui-ai <huggingface.co/huihui-ai>Subject: Huihui-DeepSeek-V4.1-Flash-1017-abliterated-GGUF
From: huihui-ai <huggingface.co/huihui-ai>Subject: Huihui-Qwen3.8-27B-abliterated-GGUF
From: alesha-pro <huggingface.co/alesha-pro>Subject: Qwen3.8-Flash-Next-abliterated-GSQ-RCO-Strata-GGUF