GLM-4.7-Flash-Grande-Heretic-UNCENSORED-42B-A3B
42BGLMheretic
from Olafangensan/GLM-4.7-Flash-heretic
↓ 5.2K♥ 393 repos
GLM-4.7-Flash-Uncensored-Heretic-NEO-CODE
GLM-4.7-Flash-Uncensored-Heretic-NEO-CODE is a Heretic-ablated variant of Olafangensan/GLM-4.7-Flash-heretic, published on Hugging Face by DavidAU. It is mit licence. It is distributed across 12 repositories in GGUF format, totalling 40K downloads.
Specification
- Model name
- GLM-4.7-Flash-Uncensored-Heretic-NEO-CODE
- Source repository
- DavidAU/GLM-4.7-Flash-Uncensored-Heretic-NEO-CODE-Imatrix-MAX-GGUF
- Base model
- Olafangensan/GLM-4.7-Flash-heretic
- Publisher
- DavidAU
- Parameters
- Not determinable from name
- Hardware class
- Unknown
- Licence
- mit
- Task
- Text generation
- Context window
- 200K tokens (as documented)
- Ablation scope
- Not stated by the publisher
- Formats available
- GGUF
- First indexed
- 22 Jan 2026
- Last updated
- 13 Jul 2026
Ablation technique
How GLM-4.7-Flash-Uncensored-Heretic-NEO-CODE was modified, and what that implies.
Heretic
Automated directional ablation via the Heretic toolchain, which searches for the refusal direction and applies it with a KL-divergence budget so general capability is preserved.
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
“Specialized and Enhanced UNCENSORED/HERETIC GGUF quants for the new GLM-4.7-Flash, 30B-A3B MOE, mixture of experts model.”
Running it
Commands are templates — confirm the exact repository and quant file before use.
llama.cpp / GGUF
hf download DavidAU/GLM-4.7-Flash-Uncensored-Heretic-NEO-CODE-Imatrix-MAX-GGUF --local-dir ./glm-4.7-flash-uncensored-heretic-neo-code
llama-cli -m ./glm-4.7-flash-uncensored-heretic-neo-code/<file>.gguf -p "..."Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "DavidAU/GLM-4.7-Flash-Uncensored-Heretic-NEO-CODE-Imatrix-MAX-GGUF"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve DavidAU/GLM-4.7-Flash-Uncensored-Heretic-NEO-CODE-Imatrix-MAX-GGUF --trust-remote-codeDownloads and variants (11)
Every published repository of GLM-4.7-Flash-Uncensored-Heretic-NEO-CODE, including quantised re-releases by other authors.
Security-team assessment
Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.
- GLM-4.7-Flash-Uncensored-Heretic-NEO-CODE 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 Olafangensan/GLM-4.7-Flash-heretic’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-4.7-Flash-Uncensored-Heretic-NEO-CODE is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with DavidAU, and does not independently verify publisher claims. See responsible use.