Qwen3.8-Flash-Next-GSQ-RCO-abliterated
Qwen
from ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF
↓ 3.6M♥ 6746 repos
Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-abliterated
Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-abliterated is a refusal-ablated variant of ukisai/Swift1.5-Qwen3.8-Flash-Next, published on Hugging Face by SC117. It is other licence. It is distributed across 7 repositories in GGUF format, totalling 463.9K downloads.
Specification
- Model name
- Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-abliterated
- Source repository
- SC117/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-abliterated-GGUF
- Base model
- ukisai/Swift1.5-Qwen3.8-Flash-Next
- Publisher
- SC117
- Parameters
- Not determinable from name
- VRAM required
- Unknown — no published parameter count
- Hardware class
- Unknown
- Licence
- other
- Task
- Image text to text
- Context window
- 41K tokens (as documented)
- Ablation scope
- Not stated by the publisher
- Formats available
- GGUF
- First indexed
- 3 Oct 2026
- Last updated
- 24 Oct 2026
Ablation technique
How Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-abliterated was modified, and what that implies.
Abliteration (directional ablation)
The single residual-stream direction that mediates refusal is identified from harmful/harmless prompt pairs and projected out of the model weights.
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 refusal direction removed from UkisAI's reasoning-efficient derivative of Qwen3.8-Flash-Next. 144 tensors across all 48 layers swap in ready-made abliterated weights by byte-level transplant — every GSQ value and scale is left untouched, the file size moves by less than 0.2%, and the reasoning-efficiency of Swift...”
Running it
Commands are templates — confirm the exact repository and quant file before use.
llama.cpp / GGUF
hf download SC117/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-abliterated-GGUF --local-dir ./swift-1.5-qwen3.8-flash-next-gsq-rco-abliterated
llama-cli -m ./swift-1.5-qwen3.8-flash-next-gsq-rco-abliterated/<file>.gguf -p "..."Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "SC117/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-abliterated-GGUF"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve SC117/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-abliterated-GGUF --trust-remote-codeDownloads and variants (6)
Every published repository of Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-abliterated, including quantised re-releases by other authors.
Security-team assessment
Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.
- Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-abliterated 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.
- Declared licence is other, but the terms that bind you are ukisai/Swift1.5-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 Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-abliterated is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with SC117, and does not independently verify publisher claims. See responsible use.