orcarouter_GLM-5.3-Flash-Uncensored
Otheruncensored
from orcarouter/GLM-5.3-Flash-Uncensored-FP8
↓ 219.8K♥ 422 repos
Sakura-MiniMax-Uncensored
Sakura-MiniMax-Uncensored is a abliterated and uncensored variant of MiniMaxAI/MiniMax-H3, published on Hugging Face by webmp3. It is other licence. It is distributed across 2 repositories in GGUF format, totalling 65.8K downloads.
Specification
- Model name
- Sakura-MiniMax-Uncensored
- Source repository
- webmp3/Sakura-MiniMax-H3-Uncensored-GGUF
- Base model
- MiniMaxAI/MiniMax-H3
- Publisher
- webmp3
- Parameters
- Not determinable from name
- VRAM required
- Unknown — no published parameter count
- Hardware class
- Unknown
- Licence
- other
- Task
- Image text to video
- Context window
- Not documented
- Ablation scope
- Not stated by the publisher
- Formats available
- GGUF
- First indexed
- 13 Oct 2026
- Last updated
- 17 Oct 2026
Ablation technique
How Sakura-MiniMax-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
“The text encoder of MiniMax-H3 (the first 50 language layers of Qwen3-VL-32B plus its vision tower, passed to the video model with --llm) with the language weights of an abliterated (uncensored) Qwen3-VL-32B-Instruct, as GGUF for stable-diffusion.cpp. Independent work, not made, reviewed or endorsed by MiniMax...”
Running it
Commands are templates — confirm the exact repository and quant file before use.
llama.cpp / GGUF
hf download webmp3/Sakura-MiniMax-H3-Uncensored-GGUF --local-dir ./sakura-minimax-uncensored
llama-cli -m ./sakura-minimax-uncensored/<file>.gguf -p "..."Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "webmp3/Sakura-MiniMax-H3-Uncensored-GGUF"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve webmp3/Sakura-MiniMax-H3-Uncensored-GGUF --trust-remote-codeDownloads and variants (1)
The only published repository of Sakura-MiniMax-Uncensored.
| Repository | Format | Downloads |
|---|---|---|
| webmp3/Sakura-MiniMax-H3-Uncensored-GGUFsource | GGUF | 65.8K |
Security-team assessment
Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.
- Sakura-MiniMax-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.
- 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 MiniMaxAI/MiniMax-H3’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 Sakura-MiniMax-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 webmp3, and does not independently verify publisher claims. See responsible use.