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

stepenZEN/DeepSeek-R1-Distill-Llama-70B-Abliterated

stepenZEN Llama 71B
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/stepenZEN%2FDeepSeek-R1-Distill-Llama-70B-Abliterated"
Response includes
  • classification m1
  • files 37
  • hub_downloads_all_time 85
  • author_summary 7 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
85
17 last 30d - stable
Likes
1
Model age
20mo ago
created 2025-02-01
Downloads over time
Now96→from2↑4,700%
035701052 on Jan 29, 202596 on Oct 1196 on Oct 10Jan '25Apr '25Jul '25Oct '25JanAprJulOct
Jan 29, 2025 → Oct 11 · 128 snapshots · spans 620 days

Metadata

Tags
safetensors llama region:us

Related

Total size
131 GB
Files
37
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2025-02-01 02:18

Files by quantization

Auxiliary files 37 files 131 GB
model-00008-of-00030.safetensors 4.66 GB 97afbcac download
model-00013-of-00030.safetensors 4.66 GB c7816c2c download
model-00018-of-00030.safetensors 4.66 GB eaf90f72 download
model-00023-of-00030.safetensors 4.66 GB f3e07bf9 download
model-00028-of-00030.safetensors 4.66 GB 9c266f9c download
model-00003-of-00030.safetensors 4.66 GB 436ffad9 download
model-00029-of-00030.safetensors 4.63 GB 734811f7 download
model-00009-of-00030.safetensors 4.63 GB 7216e7b6 download
model-00014-of-00030.safetensors 4.63 GB 8ff5b2bb download
model-00019-of-00030.safetensors 4.63 GB 70e8f2f5 download
model-00024-of-00030.safetensors 4.63 GB e448afbc download
model-00004-of-00030.safetensors 4.63 GB fbf7103c download
model-00006-of-00030.safetensors 4.34 GB fe6de3f7 download
model-00007-of-00030.safetensors 4.34 GB 38e03444 download
model-00011-of-00030.safetensors 4.34 GB 52575659 download
model-00012-of-00030.safetensors 4.34 GB d37e9398 download
model-00016-of-00030.safetensors 4.34 GB 932097f5 download
model-00017-of-00030.safetensors 4.34 GB e283ed62 download
model-00021-of-00030.safetensors 4.34 GB 05379e5e download
model-00022-of-00030.safetensors 4.34 GB da4c3071 download
model-00026-of-00030.safetensors 4.34 GB c5713413 download
model-00027-of-00030.safetensors 4.34 GB 2df6ce5b download
model-00002-of-00030.safetensors 4.34 GB bd23a65c download
model-00005-of-00030.safetensors 4.34 GB 39ac776e download
model-00010-of-00030.safetensors 4.34 GB 53747842 download
model-00015-of-00030.safetensors 4.34 GB 74dc2b04 download
model-00020-of-00030.safetensors 4.34 GB 46ca8ea3 download
model-00025-of-00030.safetensors 4.34 GB e81c3665 download
model-00001-of-00030.safetensors 4.27 GB 0ec3f1c6 download
model-00030-of-00030.safetensors 1.96 GB ee0b056e download
tokenizer.json 16.4 MB 26c881aa download
model.safetensors.index.json 58.2 KB 37b1afe6 download
tokenizer_config.json 51.7 KB e02acbac download
.gitattributes 1.53 KB 52373fe2 download
config.json 930 B b8a9a808 download
special_tokens_map.json 371 B d53f816e download
generation_config.json 155 B 168834c9 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