GLM-5.3-Flash-Uncensored
GLMuncensored
from zai-org/GLM-5.3-Flash
↓ 125.8K♥ 31642 repos
GLM-5.2-Uncensored-Colibri
GLM-5.2-Uncensored-Colibri is a abliterated and uncensored variant of jlnsrk/GLM-5.2-colibri-int4, published on Hugging Face by annelo. It is mit licence. It is distributed across 2 repositories in FP8 format, totalling 20.6K downloads.
Specification
- Model name
- GLM-5.2-Uncensored-Colibri
- Source repository
- annelo/GLM-5.2-FP8-Uncensored-Colibri-Int4
- Base model
- jlnsrk/GLM-5.2-colibri-int4
- Publisher
- annelo
- Parameters
- Not determinable from name
- VRAM required
- Unknown — no published parameter count
- Hardware class
- Unknown
- Licence
- mit
- Task
- Text generation
- Context window
- Not documented
- Ablation scope
- Not stated by the publisher
- Formats available
- FP8
- First indexed
- 13 Jul 2026
- Last updated
- 19 Jul 2026
Ablation technique
How GLM-5.2-Uncensored-Colibri was modified, and what that implies.
Abliteration + uncensored fine-tune
Directional ablation combined with additional fine-tuning on unfiltered data, so behaviour diverges from the base model beyond refusal removal alone.
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
“This is a Colibri-compatible int4 conversion of zandenAI/GLM-5.2-FP8-Uncensored.”
Running it
Commands are templates — confirm the exact repository and quant file before use.
Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "annelo/GLM-5.2-FP8-Uncensored-Colibri-Int4"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve annelo/GLM-5.2-FP8-Uncensored-Colibri-Int4 --trust-remote-codeDownloads and variants (1)
The only published repository of GLM-5.2-Uncensored-Colibri.
| Repository | Format | Downloads |
|---|---|---|
| annelo/GLM-5.2-FP8-Uncensored-Colibri-Int4source | FP8 | 20.6K |
Security-team assessment
Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.
- GLM-5.2-Uncensored-Colibri 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.
- This release adds fine-tuning on unfiltered data, so its behaviour diverges from the base model beyond refusal removal — differences you measure cannot be attributed to ablation alone.
- Declared licence is mit, but the terms that bind you are jlnsrk/GLM-5.2-colibri-int4’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-5.2-Uncensored-Colibri is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with annelo, and does not independently verify publisher claims. See responsible use.