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

RoadToNowhere/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored-int8wo-g128

RoadToNowhere Qwen 35B 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/RoadToNowhere%2FQwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored-int8wo-g128"
Response includes
  • classification m1
  • files 15
  • hub_downloads_all_time 78
  • author_summary 6 models
  • readme_text full
Try next
GET/models?author=RoadToNowhere
All 6 models by RoadToNowhere
 GET/models?family=qwen&method=m1
Sibling qwen models · same method
 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
78
12 last 30d - stable
Likes
0
Model age
18mo ago
created 2025-04-01
Downloads over time
Now84→from0↑0%
03162920 on Mar 26, 202584 on Oct 1184 on Oct 5Mar '25Jun '25Sep '25Dec '25MarJunSep
Mar 26, 2025 → Oct 11 · 120 snapshots · spans 564 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.

RoadToNowhere/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored-w8a8 this lineage
RoadToNowhere/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored-int8wo-g128↓ 12

Metadata

Tags
pytorch qwen2 base_model:RoadToNowhere/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored-int8wo-g128 base_model:quantized:RoadToNowhere/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored-int8wo-g128 torchao region:us

Related

Other by RoadToNowhere
Qwen3-32B-abliterated-Q4_K_M-GGUF 11K QwQ-32B-abliterated-exl2-4.85bpw 15 Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored-bnb-4bit 15 QwenLong-L1-32B-abliterated-Q4_K_M-GGUF 13 Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored-AWQ-int4 2
Total size
32.4 GB
Files
15
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2025-04-01 22:35
Source huggingface.co/RoadToNowhere/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored-int8wo-g128 ↗ Base model RoadToNowhere/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored-w8a8 ↗

Files by quantization

Auxiliary files 15 files 32.4 GB
pytorch_model-00001-of-00008.bin 4.63 GB fe4ce9d2 download
pytorch_model-00002-of-00008.bin 4.61 GB dac3f39d download
pytorch_model-00003-of-00008.bin 4.55 GB 115d0973 download
pytorch_model-00004-of-00008.bin 4.55 GB 7ed54908 download
pytorch_model-00005-of-00008.bin 4.55 GB ebf50ac8 download
pytorch_model-00006-of-00008.bin 4.55 GB d0aa5265 download
pytorch_model-00007-of-00008.bin 4.55 GB dcd33212 download
pytorch_model-00008-of-00008.bin 406 MB a4570fca download
tokenizer.json 6.71 MB 443909a6 download
pytorch_model.bin.index.json 60.8 KB 41fa19b3 download
tokenizer_config.json 7.89 KB bec9032c download
.gitattributes 1.48 KB a6344aac download
config.json 938 B 3cf94ef4 download
README.md 745 B 2effcfdb download
special_tokens_map.json 613 B ac23c0aa download

README current version from Hugging Face

base_model:

  • RoadToNowhere/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored-w8a8

RoadToNowhere/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored-w8a8 (Quantized)

Description

This model is a quantized version of the original model RoadToNowhere/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored-w8a8. It has been quantized using int8_weight_only quantization with torchao.

Quantization Details

  • Quantization Type: int8_weight_only
  • Group Size: None

Usage

You can use this model in your applications by loading it directly from the Hugging Face Hub:

from transformers import AutoModel

model = AutoModel.from_pretrained("RoadToNowhere/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored-w8a8")

README history 1 version

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

  1. 2025-04-01Upload folder using huggingface_huba77c67b745 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