supergemma4-26b-uncensored-v2
26BOtheruncensored
from google/gemma-4-26B-A4B-it
↓ 394K♥ 98442 repos
Hy-MT2-30B-A3B-uncensored-heretic
Hy-MT2-30B-A3B-uncensored-heretic is a Heretic-ablated variant of OS-Software/Hy-MT2-30B-A3B-uncensored-heretic, published on Hugging Face by OS-Software. It is 30B total parameters (mixture-of-experts), 48GB VRAM class class and apache-2.0 licence. It is distributed across 6 repositories in GGUF, Transformers and GGUF (imatrix) formats, totalling 6.6K downloads.
Specification
- Model name
- Hy-MT2-30B-A3B-uncensored-heretic
- Source repository
- OS-Software/Hy-MT2-30B-A3B-uncensored-heretic
- Publisher
- OS-Software
- Parameters
- 30B (mixture-of-experts)
- Hardware class
- 25B – 50B — 48GB VRAM class
- Licence
- apache-2.0
- Task
- Translation
- Context window
- Not documented
- Ablation scope
- Not stated by the publisher
- Formats available
- GGUF, Transformers, GGUF (imatrix)
- First indexed
- 29 Aug 2026
- Last updated
- 31 Aug 2026
Ablation technique
How Hy-MT2-30B-A3B-uncensored-heretic 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
“Note: A new custom mixed-language dataset was used for evaluation. Japanese-language datasets were used only to measure KLD and refusal rate.”
Running it
Commands are templates — confirm the exact repository and quant file before use.
llama.cpp / GGUF
hf download mradermacher/Hy-MT2-30B-A3B-uncensored-heretic-i1-GGUF --local-dir ./hy-mt2-30b-a3b-uncensored-heretic
llama-cli -m ./hy-mt2-30b-a3b-uncensored-heretic/<file>.gguf -p "..."Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "OS-Software/Hy-MT2-30B-A3B-uncensored-heretic"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve OS-Software/Hy-MT2-30B-A3B-uncensored-heretic --trust-remote-codeDownloads and variants (5)
Every published repository of Hy-MT2-30B-A3B-uncensored-heretic, including quantised re-releases by other authors.
| Repository | Format | Downloads |
|---|---|---|
| mradermacher/Hy-MT2-30B-A3B-uncensored-heretic-i1-GGUF | GGUF (imatrix) | 4.3K |
| mradermacher/Hy-MT2-30B-A3B-uncensored-heretic-GGUF | GGUF | 2K |
| OS-Software/Hy-MT2-30B-A3B-uncensored-heretic-GGUF | GGUF | 277 |
| OS-Software/Hy-MT2-30B-A3B-uncensored-hereticsource | Transformers | 45 |
| 0xSojalSec/Hy-MT2-30B-A3B-uncensored-heretic | Transformers | 18 |
Security-team assessment
Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.
- Hy-MT2-30B-A3B-uncensored-heretic 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.
- Capability is inherited from OS-Software/Hy-MT2-30B-A3B-uncensored-heretic, not added by ablation — at 30B parameters, expect roughly the base model’s competence, minus some instruction-following fidelity.
- The publisher does not state which layers were ablated, so assume nothing about refusal consistency — probe it directly.
- Declared licence is apache-2.0, but the terms that bind you are OS-Software/Hy-MT2-30B-A3B-uncensored-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 Hy-MT2-30B-A3B-uncensored-heretic is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with OS-Software, and does not independently verify publisher claims. See responsible use.