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

johnnyeric/DeepSeek-R1-0528-Qwen3-8B-abliterated-nvfp4

johnnyeric Deepseek 3.5B
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/johnnyeric%2FDeepSeek-R1-0528-Qwen3-8B-abliterated-nvfp4"
Response includes
  • classification m1
  • files 12
  • hub_downloads_all_time 95
  • author_summary 3 models
  • readme_text full
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)
Refusal direction extracted via
Extraction technique

Difference-of-means

Confidence
MEDIUM
Why we say so
primary_method=M1; difference-of-means is the reference extraction for M1/M3 (Arditi 2024)
Downloads · lifetime
95
27 last 30d - stable
Likes
0
Model age
10mo ago
created 2025-11-19
Downloads over time
Now110→from5↑2,100%
040801215 on Nov 19, 2025110 on Oct 11Nov '25JanMarMayJulSep
Nov 19, 2025 → Oct 11 · 86 snapshots · spans 326 days

Metadata

Tags
safetensors qwen3 8-bit compressed-tensors region:us

Related

Total size
5.96 GB
Files
12
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2025-11-19 11:57

Files by quantization

Auxiliary files 12 files 5.97 GB
model-00001-of-00002.safetensors 4.64 GB fcb0eebe download
model-00002-of-00002.safetensors 1.31 GB 22673065 download
tokenizer.json 10.9 MB 93d5fd6d download
model.safetensors.index.json 101 KB 3242e007 download
tokenizer_config.json 5.46 KB c4657dc1 download
chat_template.jinja 3.05 KB 7641578b download
config.json.bak 3.01 KB df41c2ed download
config.json 2.86 KB 0e267669 download
.gitattributes 1.53 KB 52373fe2 download
special_tokens_map.json 485 B 1d385d62 download
recipe.yaml 130 B c3664c0b download
generation_config.json 125 B c47da04e download

README

The author did not publish a README.

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