Get the app
← back to catalog · registered 2026-09-18 17:56

jakeatx/ATX-Swift-Qwen3.8-27B-Uncensored-PTQ1_0-MTP-GGUF

jakeatx 27B GGUF second-order 
curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/jakeatx%2FATX-Swift-Qwen3.8-27B-Uncensored-PTQ1_0-MTP-GGUF"
Response includes
  • classification m-uncensored
  • files 3
  • author_summary 3 models
  • readme_text full
Try next
GET/models?author=jakeatx
All 3 models by jakeatx
 GET/methods/m-uncensored
What "m-uncensored" means · taxonomy
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
How we label → About M-U →
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 · 30-day
0
Likes
0
Model age
today
created 2026-09-18

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.

d0xin/Swift-Qwen3.8-27B-Uncensored-BF16↓ 225 this lineage
jakeatx/ATX-Swift-Qwen3.8-27B-Uncensored-PTQ1_0-MTP-GGUF

Metadata

License
other
Tags
gguf llama.cpp qwen3_8 ternary ptq1_0 uncensored mtp text-generation base_model:d0xin/Swift-Qwen3.8-27B-Uncensored-BF16 base_model:quantized:d0xin/Swift-Qwen3.8-27B-Uncensored-BF16 license:other endpoints_compatible

Related

Other by jakeatx
ATX-Swift-Qwen3.8-27B-Uncensored-IQ4_XS-M-GGUF 638 ATX-Swift-Qwen3.8-27B-Uncensored-TQ2_0-MTP-GGUF 0
Same base model
mradermacher/Swift-Qwen3.8-27B-Uncensored-BF16-GGUF 2K jakeatx/ATX-Swift-Qwen3.8-27B-Uncensored-IQ4_XS-M-GGUF 638 noname222/Swift-Qwen3.8-27B-Uncensored-MTP-GGUF 292 wacomctl672/Swift-Qwen3.8-27B-Uncensored-ninfer3090 285 greglechin/Swift-Qwen3.8-27B-Uncensored-GPTQ-Int4-sym-G128-MTP-BF16 83
Total size
6.70 GB
Files
3
Quantizations
1
Registered
2026-09-18 17:56
Last updated on HF
2026-09-18 17:29
Source huggingface.co/jakeatx/ATX-Swift-Qwen3.8-27B-Uncensored-PTQ1_0-MTP-GGUF ↗ Base model d0xin/Swift-Qwen3.8-27B-Uncensored-BF16 →

Files by quantization

Auxiliary files 3 files 6.70 GB
ATX-Swift-Qwen3.8-27B-Uncensored-PTQ1_0-MTP.gguf 6.70 GB c7c47656 download
.gitattributes 1.57 KB 7f71cac1 download
README.md 1.17 KB 84c444a3 download

README current version from Hugging Face

license: other
license_name: swift-open-license-1.0
library_name: gguf
pipeline_tag: text-generation
base_model: d0xin/Swift-Qwen3.8-27B-Uncensored-BF16
tags:

  • gguf
  • llama.cpp
  • qwen3_8
  • ternary
  • ptq1_0
  • uncensored
  • mtp

ATX-Swift-Qwen3.8-27B-Uncensored-PTQ1_0-MTP-GGUF

Ternary 1.75-bit quantization (PTQ1_0) with native Multi-Token Prediction (MTP) draft head for d0xin/Swift-Qwen3.8-27B-Uncensored-BF16.

Overview

  • Quant Format: PTQ1_0 (1.75 bpw ternary, 5 trits packed per byte, ~2.10 BPW container with critical tensors preserved).
  • MTP Speculative Decoding: Native layer 64 (blk.64.*) fused directly into the model (qwen35.block_count: 65). Ready for self-speculative decoding in llama.cpp and llamAmpere without needing an external drafter model.
  • Size: 7,199,369,088 bytes (6.70 GiB)
  • SHA256: c7c47656be2f50a6a37d50e36d0bf5fa47d9d563243e6dc2ae2acaa0363218f9

Usage with llama.cpp / llamAmpere

llama-server -m ATX-Swift-Qwen3.8-27B-Uncensored-PTQ1_0-MTP.gguf   -ngl 99 -fa on -c 32768   --spec-type draft-mtp --spec-draft-n-max 3 --spec-draft-p-min 0.45
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 app" button that hands off directly to a local runtime of your choice - Infrahuman, LM Studio, or Ollama. No API keys, no subscription, no prompt leakage.

See supported apps Browse the catalog