Get the app
← back to catalog · registered 2026-10-21 15:00

dsfsfdff/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-abliterated-IQ3_S-GGUF

dsfsfdff GGUF MoE 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/dsfsfdff%2FSwift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-abliterated-IQ3_S-GGUF"
Response includes
  • classification m8
  • files 4
  • author_summary 1 models
  • readme_text full
Try next
GET/methods/m8
What "m8" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M8
Primary method

Repackaging (quantization)

Applied on top of direct removal inherited from the base model.
Confidence
MEDIUM
Inherited from base model
M1 Direct removal →
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=1
  • assume M1 (base ablation) + M8 (GGUF quant) - default when producer unknown
How we label → About M8 →
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 2026-10-21

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.

SC117/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-abliterated-GGUF↓ 223,983 this lineage
dsfsfdff/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-abliterated-IQ3_S-GGUF

Metadata

Tags
gguf llama-cpp strata abliterated moe qwen3.8 flash-next iq3_s text-generation base_model:SC117/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-abliterated-GGUF base_model:quantized:SC117/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-abliterated-GGUF endpoints_compatible
Total size
36.0 GB
Files
4
Quantizations
1
Registered
2026-10-21 15:00
Last updated on HF
2026-10-21 15:03
Source huggingface.co/dsfsfdff/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-abliterated-IQ3_S-GGUF ↗ Base model SC117/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-abliterated-GGUF →

Files by quantization

Auxiliary files 4 files 36.0 GB
Swift-Qwen3.8-Flash-Next-GSQ-RCO-abliterated-IQ3_S-00003-of-00003.gguf 22.3 GB 94271566 download
Swift-Qwen3.8-Flash-Next-GSQ-RCO-abliterated-IQ3_S-00002-of-00003.gguf 13.7 GB eb2e8521 download
.gitattributes 1.69 KB c88a1e43 download
README.md 1.27 KB b9cf0682 download

README current version from Hugging Face

base_model: SC117/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-abliterated-GGUF
library_name: gguf
pipeline_tag: text-generation
tags:

  • gguf
  • llama-cpp
  • strata
  • abliterated
  • moe
  • qwen3.8
  • flash-next
  • iq3_s

Swift 1.5 Qwen3.8-Flash-Next GSQ-RCO abliterated — IQ3_S (3-Shard Distribution)

Re-sharded version of SC117/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-abliterated-GGUF split into 3 shards specifically designed for constrained-storage environments (such as Kaggle / Colab with limited working partitions):

Shard File Size Tensors
Swift-Qwen3.8-Flash-Next-GSQ-RCO-abliterated-IQ3_S-00001-of-00003.gguf 44.85 GB 373
Swift-Qwen3.8-Flash-Next-GSQ-RCO-abliterated-IQ3_S-00002-of-00003.gguf 13.71 GB 329
Swift-Qwen3.8-Flash-Next-GSQ-RCO-abliterated-IQ3_S-00003-of-00003.gguf 23.98 GB 522
Total 83.54 GB 1,224

Highlights

  • 100% bit-exact: Identical quantization weights as SC117 / UkisAI Swift 1.5 GSQ-RCO.
  • Kaggle / Constrained-disk Ready: Shard 2 is under 15 GB to easily fit in /kaggle/working while Shards 1 & 3 fit within /tmp (< 70 GB).
  • Native support in Strata and llama.cpp.
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.

Get the app Browse the catalog
Open in Abliteration