Get the app
← back to catalog · registered 2026-08-22 13:56

Shiftedx/ornith-1.0-35b-abliterated-mxfp4-mlx

Shiftedx 35B MoE
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/Shiftedx%2Fornith-1.0-35b-abliterated-mxfp4-mlx"
Response includes
  • classification m1
  • files 17
  • hub_downloads_all_time 442
  • author_summary 24 models
  • readme_text full
Try next
GET/models?author=Shiftedx
All 24 models by Shiftedx
 GET/methods/m1
What "m1" means · taxonomy
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)
How we label → About M1 →
Refusal direction extracted via
Extraction technique

Difference-of-means

FromArditi et al. (2024) ↗
Confidence
MEDIUM
Why we say so
primary_method=M1; difference-of-means is the reference extraction for M1/M3 (Arditi 2024)
What is a refusal direction? → Read the paper ↗
Downloads · lifetime
442
13 last 30d - cooling
Likes
0
Model age
3mo ago
created 2026-07-05
Downloads over time
Now446→from245↑82%
235312389466245 on Jul 15446 on Oct 11446 on Oct 10JulAugSepOct
Jul 15 → Oct 11 · 53 snapshots · spans 88 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.

deepreinforce-ai/Ornith-1.0-35B this lineage
Shiftedx/ornith-1.0-35b-abliterated-mxfp4-mlx↓ 13

Metadata

License
other
Languages
en
Tags
mlx safetensors qwen3_5_moe apple-silicon ornith mxfp4 abliterated en base_model:ornith-ai/Ornith-1.0-35B base_model:quantized:ornith-ai/Ornith-1.0-35B license:other 4-bit

Related

Other by Shiftedx
qwen3.8-27b-aeon-ultimate-uncensored-attention8-bf16recurrence-vision-mtplx 1K qwen3.8-27b-aeon-ultimate-uncensored-mxfp4-vision-mtplx 1K Qwen3.8-27B-AEON-ULTIMATE-UNCENSORED-MLX-MIXED-VISION-MTPLX 543 qwopus3.8-27b-flash-abliterated-mxfp4-vision-mtplx 541 ornith-1.5-35b-a3b-abliterated-attention8-bf16recurrence-vision-mtplx 474
Same base model
huihui-ai/Huihui-Ornith-1.0-35B-abliterated-GGUF 11K AEON-7/Ornith-1.0-35B-AEON-Ultimate-Uncensored-BF16 8K zaakirio/Ornith-1.0-35B-uncensored-GGUF 254 Shiftedx/ornith-1.0-35b-abliterated-mxfp4-vision-mtplx 233 satgeze/Ornith-1.0-35B-abliterated-SatGeZe 168
Total size
18.0 GB
Files
17
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-07-05 23:06
Source huggingface.co/Shiftedx/ornith-1.0-35b-abliterated-mxfp4-mlx ↗ Base model deepreinforce-ai/Ornith-1.0-35B ↗

Files by quantization

Auxiliary files 17 files 18.0 GB
model-00003-of-00004.safetensors 5.00 GB 3989f453 download
model-00002-of-00004.safetensors 5.00 GB 1015e82b download
model-00001-of-00004.safetensors 4.98 GB 3dc6088c download
model-00004-of-00004.safetensors 2.18 GB 6531899b download
model-vision-00001-of-00001.safetensors 852 MB d4579339 download
tokenizer.json 19.1 MB 06b95093 download
vocab.json 6.41 MB 0aa0ce06 download
model.safetensors.index.json 161 KB 97fa6085 download
config.json 23.7 KB 06a57773 download
tokenizer_config.json 8.81 KB 1a5e6600 download
chat_template.jinja 7.36 KB 33dc1028 download
.gitattributes 1.53 KB 52373fe2 download
README.md 1023 B e2863962 download
processor_config.json 991 B 8f29fe38 download
preprocessor_config.json 390 B 2ea84a43 download
video_preprocessor_config.json 385 B 3ba673a5 download
generation_config.json 213 B 3f7527c4 download

README current version from Hugging Face

language:

  • en
    license: other
    tags:
  • mlx
  • apple-silicon
  • ornith
  • mxfp4
  • abliterated
    base_model: deepreinforce-ai/Ornith-1.0-35B

ornith-1.0-35b-abliterated-mxfp4-mlx

MXFP4 MLX build of deepreinforce-ai/Ornith-1.0-35B with a local abliteration pass to reduce over-refusal while preserving normal task behavior.

Notes

  • Publisher: Shiftedx
  • Format: MLX safetensors
  • Quantization: MXFP4
  • Vision: yes
  • Default chat behavior: thinking off unless explicitly enabled
  • Privacy: local-first artifact; no service endpoint, telemetry, private prompts, or host-specific paths are included

Validation

Hardware reference: Apple M4 Max Apple Silicon with 64 GB unified memory.

  • Refusal-marker mini-suite: 0% after abliteration; baseline was 100%.
  • Benign-sensitive refusal rate: 0%.
  • Utility mini-suite: 100%.
  • Code mini-suite: 100%.
  • Vision smoke: passed on word and scene recognition.
  • LM Studio load and text smoke: passed.

Use

Load with LM Studio or MLX-compatible tooling on Apple Silicon.

README history 2 versions

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

  1. 2026-07-05Add validation hardware reference99ef6a11023 B
    Loading...
  2. 2026-07-05Upload validated abliterated MLX MXFP4 vision buildcc21e84948 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.

Get the app Browse the catalog
Open in Abliteration