← back to catalog · registered 2026-11-21 18:04

Kutsuya/Swift-1.5-Qwen3.8-27B-Abliterated-EXL3-4.0bpw

Kutsuya 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/Kutsuya%2FSwift-1.5-Qwen3.8-27B-Abliterated-EXL3-4.0bpw"
Response includes
  • classification m1
  • files 21
  • author_summary 2 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M1
Primary method

Direct removal

No other method signals detected in this model.
Confidence
MEDIUM
Why this label 3 signals
Method inferred from partial signals - repository name, related files, or tag patterns. Producer identity not confirmed; label may sharpen or shift as we gather more evidence.
  • 'abliterated' in name/tags
  • is_gguf=0 (base model)
  • no specific method indicators - defaulting to M1 (most common)
Refusal direction extracted via
Extraction technique

Difference-of-means

Confidence
MEDIUM
Why we say so
primary_method=M1; difference-of-means is the reference extraction for M1/M3 (Arditi 2024)
Downloads · 30-day
0
Likes
0
Model age
today
created 2026-11-21
Downloads over time
Now 0 → from 0 ↑ 0%
0011 0 on Nov 21 0 on Nov 22 Nov
Nov 21 → Nov 22 · 2 snapshots · spans 1 day

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
safetensors qwen3_5 exl3 exllamav3 qwen base_model:grimlee/Swift-1.5-Qwen3.8-27B-Abliterated base_model:quantized:grimlee/Swift-1.5-Qwen3.8-27B-Abliterated 4-bit region:us

Related

Total size
15.4 GB
Files
21
Quantizations
1
Registered
2026-11-21 18:04
Last updated on HF
2026-11-21 18:01

Files by quantization

Auxiliary files 21 files 15.4 GB
model-00001-of-00002.safetensors 7.89 GB bc66e094 download
model-00002-of-00002.safetensors 7.49 GB 7f27cc8c download
tokenizer.json 12.2 MB 0997f410 download
vocab.json 6.41 MB 0aa0ce06 download
swift-1.5-planet-demo.mp4 4.52 MB 1cda6924 download
merges.txt 3.20 MB a494e019 download
quantization_config.json 614 KB 2847fb31 download
ukisai-banner.png 301 KB 8577252b download
model.safetensors.index.json 289 KB 082b653b download
tokenizer_config.json 17.5 KB 5de744b3 download
LICENSE 13.0 KB 209a5720 download
LICENSE-APACHE-2.0 11.3 KB f938136e download
chat_template.jinja 8.74 KB c0c686f9 download
config.json 4.54 KB 35531bef download
.gitattributes 1.65 KB f5d3bb6c download
ABLITERATION_METADATA.json 1.53 KB 003a37d9 download
NOTICE 1.11 KB c4ad1a71 download
preprocessor_config.json 390 B 2ea84a43 download
video_preprocessor_config.json 385 B 3ba673a5 download
README.md 271 B a7892edc download
generation_config.json 202 B 023756cf download

README current version from Hugging Face


base_model: grimlee/Swift-1.5-Qwen3.8-27B-Abliterated
tags:

  • exl3
  • exllamav3
  • qwen

Swift-1.5-Qwen3.8-27B-Abliterated (EXL3 4.0bpw)

EXL3 4.0 bpw quantization of grimlee/Swift-1.5-Qwen3.8-27B-Abliterated created with ExLlamaV3.

README history 1 version

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

  1. 2026-11-21 Upload folder using huggingface_hub 53dccc0 271 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