Qwythos-9B-v2
9BOtheruncensored
from empero-ai/Qwythos-9B-v2
↓ 639.9K♥ 26611 repos
flux2-klein-4b-uncensored-text-encoder
flux2-klein-4b-uncensored-text-encoder is a abliterated and uncensored variant of black-forest-labs/FLUX.2-klein-4B, published on Hugging Face by ponpoke. It is 4B parameters, single consumer GPU class and other licence. It is distributed across 5 repositories in GGUF format, totalling 20.1K downloads.
Specification
- Model name
- flux2-klein-4b-uncensored-text-encoder
- Source repository
- ponpoke/flux2-klein-4b-uncensored-text-encoder
- Base model
- black-forest-labs/FLUX.2-klein-4B
- Publisher
- ponpoke
- Parameters
- 4B
- Hardware class
- 4B – 10B — single consumer GPU
- Licence
- other
- Task
- Text to image
- Context window
- Not documented
- Ablation scope
- Not stated by the publisher
- Formats available
- GGUF
- First indexed
- 27 Jan 2026
- Last updated
- 22 Jun 2026
Ablation technique
How flux2-klein-4b-uncensored-text-encoder 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.
Running it
Commands are templates — confirm the exact repository and quant file before use.
llama.cpp / GGUF
hf download ponpoke/flux2-klein-4b-uncensored-text-encoder --local-dir ./flux2-klein-4b-uncensored-text-encoder
llama-cli -m ./flux2-klein-4b-uncensored-text-encoder/<file>.gguf -p "..."Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "ponpoke/flux2-klein-4b-uncensored-text-encoder"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve ponpoke/flux2-klein-4b-uncensored-text-encoder --trust-remote-codeDownloads and variants (4)
Every published repository of flux2-klein-4b-uncensored-text-encoder, including quantised re-releases by other authors.
| Repository | Format | Downloads |
|---|---|---|
| ponpoke/flux2-klein-4b-uncensored-text-encodersource | GGUF | 12.7K |
| nerualdreming/flux2-klein-4b-uncensored-text-encoder | GGUF | 2.7K |
| WeReCooking/flux2-klein-4B-uncensored-text-encoder | GGUF | 2.6K |
| Cordux/flux2-klein-4B-uncensored-text-encoder | GGUF | 2.2K |
Security-team assessment
Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.
- flux2-klein-4b-uncensored-text-encoder 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 black-forest-labs/FLUX.2-klein-4B, 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 black-forest-labs/FLUX.2-klein-4B’s — a re-release cannot grant more than its parent.
- The source repository is gated, so downloading requires accepting the publisher’s terms.
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 flux2-klein-4b-uncensored-text-encoder is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with ponpoke, and does not independently verify publisher claims. See responsible use.