Satyr-V0.1-4B
4BOtheruncensored
from Qwen/Qwen3-4B-Thinking-2507
↓ 8.2K♥ 2497 repos
Minecraftism-4B-Thinking-Uncensored
Minecraftism-4B-Thinking-Uncensored is a abliterated and uncensored variant of Qwen/Qwen3-4B-Thinking-2507, published on Hugging Face by mr-sus. It is 4B parameters, single consumer GPU class and other licence. It is distributed across 5 repositories in Transformers, GGUF and GGUF (imatrix) formats, totalling 7.6K downloads.
Specification
- Model name
- Minecraftism-4B-Thinking-Uncensored
- Source repository
- mr-sus/Minecraftism-4B-Thinking-Uncensored
- Base model
- Qwen/Qwen3-4B-Thinking-2507
- Publisher
- mr-sus
- Parameters
- 4B
- VRAM required
- ~3.2 GB at Q4_K_M, 4k context (estimated) — runs on 4 GB cards
- Hardware class
- 4B – 10B — single consumer GPU
- Licence
- other
- Task
- Text generation
- Context window
- Not documented
- Ablation scope
- Not stated by the publisher
- Formats available
- Transformers, GGUF, GGUF (imatrix)
- First indexed
- 24 Oct 2026
- Last updated
- 3 Nov 2026
Ablation technique
How Minecraftism-4B-Thinking-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
“This page uses a third-party view counter at 2no.co; it may receive a request when the card is viewed.”
Running it
Commands are templates — confirm the exact repository and quant file before use.
llama.cpp / GGUF
hf download mr-sus/Minecraftism-4B-Thinking-Uncensored-GGUF --local-dir ./minecraftism-4b-thinking-uncensored
llama-cli -m ./minecraftism-4b-thinking-uncensored/<file>.gguf -p "..."Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "mr-sus/Minecraftism-4B-Thinking-Uncensored"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve mr-sus/Minecraftism-4B-Thinking-Uncensored --trust-remote-codeDownloads and variants (4)
Every published repository of Minecraftism-4B-Thinking-Uncensored, including quantised re-releases by other authors.
| Repository | Format | Downloads |
|---|---|---|
| mr-sus/Minecraftism-4B-Thinking-Uncensored-GGUF | GGUF | 4K |
| mradermacher/Minecraftism-4B-Thinking-Uncensored-i1-GGUF | GGUF (imatrix) | 1.9K |
| mr-sus/Minecraftism-4B-Thinking-Uncensoredsource | Transformers | 1.1K |
| mradermacher/Minecraftism-4B-Thinking-Uncensored-GGUF | GGUF | 629 |
Security-team assessment
Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.
- Minecraftism-4B-Thinking-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 Qwen/Qwen3-4B-Thinking-2507, not added by ablation — at 4B 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 other, but the terms that bind you are Qwen/Qwen3-4B-Thinking-2507’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 Minecraftism-4B-Thinking-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 mr-sus, and does not independently verify publisher claims. See responsible use.