Pyrex-8B-Instruct-Uncensored
8BOtheruncensored
from ImposterOnline/Pyrex-8B-Instruct-Uncensored
↓ 9.4K♥ 34 repos
Pyrut-8B-Instruct-Uncensored
Pyrut-8B-Instruct-Uncensored is a abliterated and uncensored variant of ImposterOnline/Pyrex-8B-Instruct-Uncensored, published on Hugging Face by mradermacher. It is 8B parameters, single consumer GPU class and mit licence. It is distributed across 4 repositories in GGUF and GGUF (imatrix) formats, totalling 5.3K downloads.
Specification
- Model name
- Pyrut-8B-Instruct-Uncensored
- Source repository
- mradermacher/Pyrut-8B-Instruct-Uncensored-i1-GGUF
- Publisher
- mradermacher
- Parameters
- 8B
- VRAM required
- ~5.6 GB at Q4_K_M, 4k context (estimated) — runs on 6 GB cards
- Hardware class
- 4B – 10B — single consumer GPU
- Licence
- mit
- Task
- Text generation
- Context window
- Not documented
- Ablation scope
- Not stated by the publisher
- Formats available
- GGUF, GGUF (imatrix)
- First indexed
- 3 Oct 2026
- Last updated
- 12 Oct 2026
Ablation technique
How Pyrut-8B-Instruct-Uncensored 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/Pyrut-8B-Instruct-Uncensored-i1-GGUF --local-dir ./pyrut-8b-instruct-uncensored
llama-cli -m ./pyrut-8b-instruct-uncensored/<file>.gguf -p "..."Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "mradermacher/Pyrut-8B-Instruct-Uncensored-i1-GGUF"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve mradermacher/Pyrut-8B-Instruct-Uncensored-i1-GGUF --trust-remote-codeDownloads and variants (3)
Every published repository of Pyrut-8B-Instruct-Uncensored, including quantised re-releases by other authors.
| Repository | Format | Downloads |
|---|---|---|
| mradermacher/Pyrut-8B-Instruct-Uncensored-i1-GGUFsource | GGUF (imatrix) | 4.8K |
| mradermacher/Pyrut-8B-Instruct-Uncensored-GGUF | GGUF | 574 |
| ImposterOnline/Pyrut-8B-Instruct-Uncensored-GGUF | GGUF | 0 |
Security-team assessment
Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.
- Pyrut-8B-Instruct-Uncensored 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 ImposterOnline/Pyrex-8B-Instruct-Uncensored, not added by ablation — at 8B parameters, expect a small model’s reasoning and a high error rate on exploit detail.
- 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 ImposterOnline/Pyrex-8B-Instruct-Uncensored’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 Pyrut-8B-Instruct-Uncensored 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.