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

Nexesenex/Llama_3.x_70b_L3.3-Tulu-3_abliterated_fusion

Nexesenex Llama 71B 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/Nexesenex%2FLlama_3.x_70b_L3.3-Tulu-3_abliterated_fusion"
Response includes
  • classification m5
  • files 38
  • benchmarks 11 entries
  • hub_downloads_all_time 52
  • author_summary 15 models
  • readme_text full
Try next
GET/models?author=Nexesenex
All 15 models by Nexesenex
 GET/models?family=llama&method=m5
Sibling llama models · same method
 GET/methods/m5
What "m5" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M5
Primary method

Mergekit merge

Applied on top of direct removal inherited from the base model.
Confidence
MEDIUM
Inherited from base model
M1 Direct removal →
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.
  • merge tag / mergekit / dare-ties in tags or name
  • no unusual architecture pattern (regular merge)
  • abliterated marker present
How we label → About M5 →
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 · lifetime
52
11 last 30d - stable
Likes
0
Descendants
2
in 2 direct forks
Model age
18mo ago
created 2025-04-09
Downloads over time
Now58→from0↑0%
043861290 on Apr 2, 202558 on Oct 11117 on Sep 24, 2025Apr '25Jul '25Oct '25JanAprJulOct
Apr 2, 2025 → Oct 11 · 119 snapshots · spans 557 days

Benchmarks

Benchmark Score Source
Entertainment 3.2 UGI
Hazardous 3.5 UGI
Natural Intelligence 33.54 UGI
Political lean -20.3% UGI
Sensitive-Info 32.66 UGI
SocPol 3.1 UGI
UGI 48.44 UGI
Willingness (10) 8 UGI
W10-Adherence 8 UGI
W10-Direct 8 UGI
Writing 31.76 UGI

Genealogy 2 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.

huihui-ai/Llama-3.3-70B-Instruct-abliterated↓ 16,741 this lineage
Nexesenex/Llama_3.x_70b_L3.3-Tulu-3_abliterated_fusion↓ 11 2 forks
mradermacher/Llama_3.x_70b_L3.3-Tulu-3_abliterated_fusion-i1-GGUF↓ 444
mradermacher/Llama_3.x_70b_L3.3-Tulu-3_abliterated_fusion-GGUF↓ 308

Metadata

Tags
transformers safetensors llama text-generation mergekit merge conversational base_model:huihui-ai/Llama-3.3-70B-Instruct-abliterated base_model:finetune:huihui-ai/Llama-3.3-70B-Instruct-abliterated text-generation-inference endpoints_compatible region:us

Related

Other by Nexesenex
Dolphin3.0-Llama3.1-1B-abliterated 35 pankajmathur_orca_mini_v9_6_1B-instruct-Abliterated-LPL 27 Llama_3.x_70b_DoppelGutenberg-L3.3_abliterated_fusion 25 Llama_3.x_70b_Gutenberg-Doppel-L3.3-TDRussel-Storywriter_abliterated_fusion 24 Llama_3.x_70b_Nemotron-L3.3_abliterated_fusion_v2 22
Same base model
bartowski/Llama-3.3-70B-Instruct-abliterated-GGUF 54K mradermacher/Llama-3.3-70B-Instruct-abliterated-GGUF 2K divinetribe/Llama-3.3-70B-Instruct-abliterated-8bit-mlx 1K jiangchengchengNLP/llama3.3-70B-instruct-abliterated-awq 861 mradermacher/Llama-3.3-70B-Instruct-abliterated-i1-GGUF 860
Total size
131 GB
Files
38
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2025-04-09 10:03
Source huggingface.co/Nexesenex/Llama_3.x_70b_L3.3-Tulu-3_abliterated_fusion ↗ Base model huihui-ai/Llama-3.3-70B-Instruct-abliterated →

Files by quantization

Auxiliary files 38 files 131 GB
model-00004-of-00030.safetensors 4.66 GB 5f2d6f26 download
model-00009-of-00030.safetensors 4.66 GB 864bec5e download
model-00019-of-00030.safetensors 4.66 GB 33a65f95 download
model-00024-of-00030.safetensors 4.66 GB bfe78a7d download
model-00014-of-00030.safetensors 4.66 GB 89e64237 download
model-00029-of-00030.safetensors 4.66 GB 626b6d26 download
model-00003-of-00030.safetensors 4.64 GB fd5c97a9 download
model-00008-of-00030.safetensors 4.64 GB 2b358606 download
model-00013-of-00030.safetensors 4.64 GB 4dcf7a70 download
model-00023-of-00030.safetensors 4.64 GB 0380feb1 download
model-00028-of-00030.safetensors 4.64 GB 0aa74953 download
model-00018-of-00030.safetensors 4.64 GB 067742e5 download
model-00001-of-00030.safetensors 4.35 GB 3177999a download
model-00007-of-00030.safetensors 4.34 GB 33fd25ef download
model-00012-of-00030.safetensors 4.34 GB 4bf71632 download
model-00017-of-00030.safetensors 4.34 GB e8c6aaef download
model-00027-of-00030.safetensors 4.34 GB ba5d47e9 download
model-00011-of-00030.safetensors 4.34 GB d103be62 download
model-00016-of-00030.safetensors 4.34 GB a1fe33d5 download
model-00021-of-00030.safetensors 4.34 GB fb9c5f14 download
model-00022-of-00030.safetensors 4.34 GB 75d1825d download
model-00002-of-00030.safetensors 4.34 GB 721d8a11 download
model-00006-of-00030.safetensors 4.34 GB 45aed9cc download
model-00026-of-00030.safetensors 4.34 GB 7d33964c download
model-00005-of-00030.safetensors 4.33 GB e9d24fdb download
model-00015-of-00030.safetensors 4.33 GB c969c70d download
model-00020-of-00030.safetensors 4.33 GB d1f6ba6f download
model-00025-of-00030.safetensors 4.33 GB 5b1861e0 download
model-00010-of-00030.safetensors 4.33 GB fb7b3fc1 download
model-00030-of-00030.safetensors 1.86 GB 5420fed3 download
tokenizer.json 16.4 MB 9400df98 download
model.safetensors.index.json 55.4 KB 2ef670b5 download
tokenizer_config.json 54.3 KB d67290da download
.gitattributes 1.53 KB 52373fe2 download
README.md 1.27 KB ca5f40bd download
config.json 941 B 534945de download
mergekit_config.yml 487 B 483f4d01 download
special_tokens_map.json 454 B 3c1d0491 download

README current version from Hugging Face

base_model:

  • huihui-ai/Llama-3.3-70B-Instruct-abliterated
  • huihui-ai/Llama-3.1-Tulu-3-70B-abliterated
    library_name: transformers
    tags:
  • mergekit
  • merge

merge

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the Arcee Fusion merge method using huihui-ai/Llama-3.3-70B-Instruct-abliterated as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

merge_method: arcee_fusion
models:
  - model: huihui-ai/Llama-3.3-70B-Instruct-abliterated
    parameters:
      weight: 1.0
  - model: huihui-ai/Llama-3.1-Tulu-3-70B-abliterated
    parameters:
      weight: 1.0
base_model: huihui-ai/Llama-3.3-70B-Instruct-abliterated
dtype: bfloat16
out_dtype: bfloat16
parameters:
  int8_mask: true
  normalize: false
  rescale: false
  filter_wise: false
  smooth: false
  allow_negative_weights: false
chat_template: auto
tokenizer:
  source: union

README history 1 version

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

  1. 2025-04-09Upload folder using huggingface_hub1c84eba1.3 KB
    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