Qwen3.8-Flash-Next-Uncensored
Qwenuncensoredgated
from Qwen/Qwen3.8-Flash-Next
↓ 1.8M♥ 1.3K34 repos
Qwen3.8-Flash-Next-Uncensored-REAP288
Qwen3.8-Flash-Next-Uncensored-REAP288 is a abliterated and uncensored variant of Qwen/Qwen3.8-Flash-Next, published on Hugging Face by butterf1ying. It is other licence. It is distributed across 2 repositories in MLX format, totalling 6.3K downloads.
Specification
- Model name
- Qwen3.8-Flash-Next-Uncensored-REAP288
- Source repository
- butterf1ying/Qwen3.8-Flash-Next-Uncensored-REAP288-MTP-MLX-4bit
- Base model
- Qwen/Qwen3.8-Flash-Next
- Publisher
- butterf1ying
- Parameters
- Not determinable from name
- VRAM required
- Unknown — no published parameter count
- Hardware class
- Unknown
- Licence
- other
- Task
- Image text to text
- Context window
- Not documented
- Ablation scope
- Not stated by the publisher
- Formats available
- MLX
- First indexed
- 3 Sept 2026
- Last updated
- 3 Sept 2026
Ablation technique
How Qwen3.8-Flash-Next-Uncensored-REAP288 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 checkpoint combines REAP-288 expert pruning, MLX 4-bit quantization, an SSD-backed N-gram table, and the model's native MTP head in a package tested with mlx-serve.”
Running it
Commands are templates — confirm the exact repository and quant file before use.
Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "butterf1ying/Qwen3.8-Flash-Next-Uncensored-REAP288-MTP-MLX-4bit"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve butterf1ying/Qwen3.8-Flash-Next-Uncensored-REAP288-MTP-MLX-4bit --trust-remote-codeDownloads and variants (1)
The only published repository of Qwen3.8-Flash-Next-Uncensored-REAP288.
| Repository | Format | Downloads |
|---|---|---|
| butterf1ying/Qwen3.8-Flash-Next-Uncensored-REAP288-MTP-MLX-4bitsource | MLX | 6.3K |
Security-team assessment
Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.
- Qwen3.8-Flash-Next-Uncensored-REAP288 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 Qwen/Qwen3.8-Flash-Next’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 Qwen3.8-Flash-Next-Uncensored-REAP288 is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with butterf1ying, and does not independently verify publisher claims. See responsible use.