← back to catalog · registered 2026-09-10 05:55

gbuzhf/Ornith-1.5-35B-A3B-Abliterated-CyberTiel-Calibrated-MTPv2-ICE-GGUF

gbuzhf 35B GGUF MoE 262K ctx
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/gbuzhf%2FOrnith-1.5-35B-A3B-Abliterated-CyberTiel-Calibrated-MTPv2-ICE-GGUF"
Response includes
  • classification m8
  • files 6
  • hub_downloads_all_time 15,389
  • author_summary 6 models
  • readme_text full
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
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
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
15K
6K last 30d - stable
Likes
16
Model age
6w ago
created 2026-09-10
Downloads over time
Now21.4K→from0↑0%
07.8K15.7K23.5K0 on Sep 1021.4K on Oct 27SepOct
Sep 10 → Oct 27 · 48 snapshots · spans 47 days

Metadata

Quantizations
BF16
Tags
gguf llama.cpp qwen35moe moe imatrix ICE mtp abliterated uncensored text-generation en zh

Related

Total size
148 GB
Files
6
Quantizations
2
Registered
2026-09-10 05:55
Last updated on HF
2026-10-07 22:14

Files by quantization

BF16 1 file 66.2 GB
Ornith-1.5-35B-A3B-Abliterated-CyberTiel_Calibrated-MTPv2-BF16.gguf 66.2 GB 9154fef3 download
Auxiliary files 5 files 81.4 GB
Ornith-1.5-35B-A3B-Abliterated-CyberTiel_Calibrated-MTPv2-25G-ICE.gguf 23.1 GB 21e8b449 download
Ornith-1.5-35B-A3B-Abliterated-CyberTiel_Calibrated-MTPv2-23G-ICE.gguf 21.3 GB 579a20a1 download
Ornith-1.5-35B-A3B-Abliterated-CyberTiel_Calibrated-MTPv2-21G-ICE.gguf 19.4 GB c7a97719 download
Ornith-1.5-35B-A3B-Abliterated-CyberTiel_Calibrated-MTPv2-19G-ICE.gguf 17.5 GB 083a0d0b download
.gitattributes 2.00 KB 791028dc download

README

The author did not publish a README.

Discussions 4 threads

  1. 2026-10-08Arrow 4.0 - Chat Template Updatedopen1 💬#4
    Loading...
  2. 2026-09-15您好gbuzhfopen2 💬#3
    Loading...
  3. 2026-09-1325G renewed with improved KLD & Recipes uploaded for all 4-Tiersopen3 💬#2
    Loading...
  4. 2026-09-10Tiel's 27K full imatrix corpus with ICE quantizationopen12 💬#1
    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