← back to catalog · registered 2026-09-28 12:57

d0xin/Swift-1.5-Qwen3.8-27B-Uncensored-FP8-NInfer

d0xin 27B second-order
Your rig guess connected
? Why do I need an app?
Reading your rig…

This is a rough estimate. Install the free app - we'll show exact numbers.

Reading real hardware from your app right now. Numbers below are exact.

Below is the per-quantization compatibility for this model.

curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/d0xin%2FSwift-1.5-Qwen3.8-27B-Uncensored-FP8-NInfer"
Response includes
  • classification m-uncensored
  • files 3
  • hub_downloads_all_time 35
  • author_summary 8 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M-U
Primary method

Uncensored (method unknown)

No other method signals detected in this model.
Confidence
LOW
Why this label 3 signals
Weak or ambiguous signals. Best guess based on catalog patterns; treat as tentative and check the evidence below.
  • 'uncensored' in name/tags but no 'abliterated' marker
  • method not identifiable from author declaration alone
  • may be DPO fine-tune, prompt engineering, or unknown technique
Refusal direction extraction

No specific extraction method could be identified for this model. The producer either did not document it or used a proprietary pipeline.

What is a refusal direction? →
Downloads · lifetime
35
19 last 30d - active
Likes
2
Model age
7w ago
created 2026-09-28
Downloads over time
Now 244 → from 0 ↑ 0%
089179268 0 on Sep 28 244 on Nov 22 244 on Nov 21 SepOctNov
Sep 28 → Nov 22 · 56 snapshots · spans 55 days

Genealogy 0 direct forks

Full fork graph →

This model's place in the market. Above: what it was derived from. Below: the tree of everything derived from it.

Metadata

Tags
ninfer qwen qwen3.8 swift fp8 blackwell local-llm base_model:d0xin/Swift-1.5-Qwen3.8-27B-Uncensored-FP8 base_model:finetune:d0xin/Swift-1.5-Qwen3.8-27B-Uncensored-FP8 region:us

Related

Total size
0 B
Files
3
Quantizations
1
Registered
2026-09-28 12:57
Last updated on HF
2026-10-01 12:17

Files by quantization

Auxiliary files 3 files 28.2 GB
Swift-1.5-Qwen3.8-27B-Uncensored-FP8.v3.ninfer 28.2 GB 59582891 download
.gitattributes 1.56 KB 076e3ea4 download
README.md 834 B c5c05eba download

README current version from Hugging Face


base_model: d0xin/Swift-1.5-Qwen3.8-27B-Uncensored-FP8
tags:

  • qwen
  • qwen3.8
  • swift
  • fp8
  • ninfer
  • blackwell
  • local-llm

Swift-1.5 Qwen3.8 27B Uncensored FP8 — NInfer

Ready-to-run NInfer artifact built from:

d0xin/Swift-1.5-Qwen3.8-27B-Uncensored-FP8

Format

This repository contains the compiled .ninfer artifact rather than the
original Hugging Face safetensors checkpoint.

Artifact generation:

  • source precision: FP8
  • NInfer format: v3
  • target workload: local inference
  • validated on NVIDIA RTX PRO 6000 Blackwell

Source checkpoint

https://huggingface.co/d0xin/Swift-1.5-Qwen3.8-27B-Uncensored-FP8

Notes

The NInfer artifact is intended for compatible NInfer runtimes.

Model behavior, architecture, provenance and licensing remain subject to
the source model and its upstream components.

README history 3 versions

The author's README evolved over time. Click a version to see its content at that point.

  1. 2026-10-01 Rename related-models navigation header db8a314 2 KB
    Loading...
  2. 2026-10-01 Cross-link d0xin model releases d7fcc4d 2 KB
    Loading...
  3. 2026-09-28 Add model card 0429b89 834 B
    Loading...
Catalog is the map. Apps are the tools.

Run models on your own machine, not in the cloud.

Every model page has an "Open in Abliteration" button that hands the model directly to the first-party desktop client, at the quantization your rig can actually run. No API keys, no subscription, no prompt leakage.

Open in Abliteration