Gemma-4-E4B-Uncensored-HauhauCS-Aggressive
Gemmauncensored
from HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive
↓ 2.6M♥ 1.1K48 repos
Tinman-gemma4-companion
Tinman-gemma4-companion is a abliterated and uncensored variant of OBLITERATUS/gemma-4-E4B-it-OBLITERATED, published on Hugging Face by mradermacher. It is apache-2.0 licence. It is distributed across 8 repositories in GGUF and GGUF (imatrix) formats, totalling 9.3K downloads.
Specification
- Model name
- Tinman-gemma4-companion
- Source repository
- mradermacher/Tinman-gemma4-companion-merged-i1-GGUF
- Base model
- OBLITERATUS/gemma-4-E4B-it-OBLITERATED
- Publisher
- mradermacher
- Parameters
- Not determinable from name
- Hardware class
- Unknown
- Licence
- apache-2.0
- Task
- Unspecified
- Context window
- Not documented
- Ablation scope
- Not stated by the publisher
- Formats available
- GGUF, GGUF (imatrix)
- First indexed
- 23 Apr 2026
- Last updated
- 2 Sept 2026
Ablation technique
How Tinman-gemma4-companion 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
“For a convenient overview and download list, visit our model page for this model.”
Running it
Commands are templates — confirm the exact repository and quant file before use.
llama.cpp / GGUF
hf download mradermacher/Tinman-gemma4-companion-merged-i1-GGUF --local-dir ./tinman-gemma4-companion
llama-cli -m ./tinman-gemma4-companion/<file>.gguf -p "..."Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "mradermacher/Tinman-gemma4-companion-merged-i1-GGUF"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve mradermacher/Tinman-gemma4-companion-merged-i1-GGUF --trust-remote-codeDownloads and variants (7)
Every published repository of Tinman-gemma4-companion, including quantised re-releases by other authors.
| Repository | Format | Downloads |
|---|---|---|
| mradermacher/Tinman-gemma4-companion-merged-i1-GGUFsource | GGUF (imatrix) | 5.6K |
| Tinman-Lab/Tinman-gemma4-companion-gguf | GGUF | 1.9K |
| mradermacher/Tinman-gemma4-companion-merged-GGUF | GGUF | 936 |
| Bedhoy/Tinman-gemma4-companion-gguf | GGUF | 363 |
| Tinman-Lab/Tinman-gemma4-companion-merged | GGUF | 339 |
| chuckb80/Tinman-gemma4-companion-merged | GGUF | 49 |
| Guile/Tinman-gemma4-companion-merged | GGUF | 43 |
Security-team assessment
Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.
- Tinman-gemma4-companion 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 apache-2.0, but the terms that bind you are OBLITERATUS/gemma-4-E4B-it-OBLITERATED’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 Tinman-gemma4-companion is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with mradermacher, and does not independently verify publisher claims. See responsible use.