Get the app
← back to catalog · registered 2026-11-04 19:02

cspenn/Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V13-dequantized-oQ4e-mtp

cspenn 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/cspenn%2FQwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V13-dequantized-oQ4e-mtp"
Response includes
  • classification unknown
  • files 17
  • author_summary 1 models
  • readme_text full
Try next
GET/methods/unknown
What "unknown" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
?
Primary method

Unclassified

No clear signals of an abliteration technique in this model.
Confidence
UNKNOWN
How we label → About ? →
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 2026-11-04

Metadata

Tags
mlx safetensors qwen3_5_moe oq quantized mtp 4-bit region:us
Total size
20.1 GB
Files
17
Quantizations
1
Registered
2026-11-04 19:02
Last updated on HF
2026-11-04 18:41
Source huggingface.co/cspenn/Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V13-dequantized-oQ4e-mtp ↗

Files by quantization

Auxiliary files 17 files 20.1 GB
model-00003-of-00005.safetensors 4.78 GB 1d14dff4 download
model-00004-of-00005.safetensors 4.78 GB 692cbb46 download
model-00002-of-00005.safetensors 4.78 GB 4a7f1246 download
model-00001-of-00005.safetensors 4.66 GB 4c14f2d5 download
model-00005-of-00005.safetensors 1.13 GB 21b67106 download
tokenizer.json 12.2 MB 5f9e4d49 download
vocab.json 6.41 MB 0aa0ce06 download
merges.txt 3.20 MB a494e019 download
model.safetensors.index.json 200 KB ea965512 download
config.json 86.8 KB 6b367264 download
oq_imatrix_report.json 32.0 KB e40cb2df download
tokenizer_config.json 16.3 KB 28d96ff3 download
chat_template.jinja 7.58 KB a8755d82 download
.gitattributes 1.53 KB 52373fe2 download
README.md 1.16 KB 102b0db0 download
preprocessor_config.json 390 B 2ea84a43 download
generation_config.json 202 B 023756cf download

README current version from Hugging Face

library_name: mlx
tags:

  • mlx
  • oq
  • quantized
  • mtp

Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V13-dequantized-oQ4e-mtp

This model was quantized using oQ (oMLX v0.7.3) mixed-precision quantization.

The effective average is 4.809 bits/weight for the complete checkpoint.

Quantization and Bit Distribution

Storage format Logical weights Share of total Tensor storage Effective bits/weight
Affine 4-bit, group 64 33.571B 93.378% 17.587 GiB 4.50
Affine 5-bit, group 128 0.489B 1.361% 0.299 GiB 5.25
Affine 6-bit, group 64 0.184B 0.510% 0.139 GiB 6.50
Affine 8-bit, group 128 0.129B 0.359% 0.124 GiB 8.25
Affine 8-bit, group 64 1.101B 3.063% 1.090 GiB 8.50
BF16 0.478B 1.329% 0.890 GiB 16.00
Total 35.952B 100% 20.128 GiB 4.809

Storage Breakdown

Component Logical weights Storage
Language model 34.661B 20.216 GB / 18.828 GiB
Vision 0.447B 0.893 GB / 0.832 GiB
MTP head 0.845B 0.503 GB / 0.468 GiB
Total 35.952B 21.612 GB / 20.128 GiB
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