GLM-5.3-Flash-Uncensored
GLMuncensored
from zai-org/GLM-5.3-Flash
↓ 125.8K♥ 31642 repos
GLM-5.3-Flash-abliterated-Maya-M
GLM-5.3-Flash-abliterated-Maya-M is a refusal-ablated variant of peasantsmith/GLM-5.3-Flash-Maya-GGUF, published on Hugging Face by alesha-pro. It is mit licence. It is distributed across 2 repositories in GGUF format, totalling 15.3K downloads.
Specification
- Model name
- GLM-5.3-Flash-abliterated-Maya-M
- Source repository
- alesha-pro/GLM-5.3-Flash-abliterated-Maya-M-GGUF
- Base model
- peasantsmith/GLM-5.3-Flash-Maya-GGUF
- Publisher
- alesha-pro
- Parameters
- Not determinable from name
- VRAM required
- Unknown — no published parameter count
- Hardware class
- Unknown
- Licence
- mit
- Task
- Image text to text
- Context window
- 256K tokens (as documented)
- Ablation scope
- Not stated by the publisher
- Formats available
- GGUF
- First indexed
- 10 Oct 2026
- Last updated
- 10 Oct 2026
Ablation technique
How GLM-5.3-Flash-abliterated-Maya-M was modified, and what that implies.
Abliteration (directional ablation)
The single residual-stream direction that mediates refusal is identified from harmful/harmless prompt pairs and projected out of the model weights.
Reported scope: Not stated by the publisher. Publishers frequently omit this, so verify behaviour empirically rather than assuming full coverage.
From the publisher’s model card
“Project Maya's Maya-M quant of GLM-5.3-Flash plus a 2.2 MB vector that removes refusals while the model runs, and a small patch for the Maya engine that applies it. On 4x RTX 3090 it decodes 56 tokens/s at a 256K context with the vector on.”
Running it
Commands are templates — confirm the exact repository and quant file before use.
llama.cpp / GGUF
hf download alesha-pro/GLM-5.3-Flash-abliterated-Maya-M-GGUF --local-dir ./glm-5.3-flash-abliterated-maya-m
llama-cli -m ./glm-5.3-flash-abliterated-maya-m/<file>.gguf -p "..."Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "alesha-pro/GLM-5.3-Flash-abliterated-Maya-M-GGUF"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve alesha-pro/GLM-5.3-Flash-abliterated-Maya-M-GGUF --trust-remote-codeDownloads and variants (1)
The only published repository of GLM-5.3-Flash-abliterated-Maya-M.
| Repository | Format | Downloads |
|---|---|---|
| alesha-pro/GLM-5.3-Flash-abliterated-Maya-M-GGUFsource | GGUF | 15.3K |
Security-team assessment
Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.
- GLM-5.3-Flash-abliterated-Maya-M will attempt offensive-security prompts that a hosted commercial model declines, which is what makes it usable for red-team corpus generation and for measuring what an unaligned model of this class produces.
- The publisher does not state which layers were ablated, so assume nothing about refusal consistency — probe it directly.
- Declared licence is mit, but the terms that bind you are peasantsmith/GLM-5.3-Flash-Maya-GGUF’s — a re-release cannot grant more than its parent.
Handling: run it isolated, put moderation in front of it if anyone outside your team can reach it, and verify the weights before loading — these are third-party artifacts. Full handling and licence guidance.
Metadata for GLM-5.3-Flash-abliterated-Maya-M is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with alesha-pro, and does not independently verify publisher claims. See responsible use.