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

NexesMess/Llama_3.x_70b_FLDx2-L3.3_abliterated_fusion

NexesMess 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/NexesMess%2FLlama_3.x_70b_FLDx2-L3.3_abliterated_fusion"
Response includes
  • classification m5
  • files 38
  • benchmarks 11 entries
  • hub_downloads_all_time 66
  • author_summary 3 models
  • readme_text full
Try next
GET/models?author=NexesMess
All 3 models by NexesMess
 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
66
16 last 30d - stable
Likes
0
Descendants
2
in 2 direct forks
Model age
18mo ago
created 2025-04-10
Downloads over time
Now72→from18↑300%
032649718 on Apr 9, 202572 on Oct 1188 on Sep 24, 2025Apr '25Jul '25Oct '25JanAprJulOct
Apr 9, 2025 → Oct 11 · 118 snapshots · spans 550 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
NexesMess/Llama_3.x_70b_FLDx2-L3.3_abliterated_fusion↓ 16 2 forks
mradermacher/Llama_3.x_70b_FLDx2-L3.3_abliterated_fusion-i1-GGUF↓ 814
mradermacher/Llama_3.x_70b_FLDx2-L3.3_abliterated_fusion-GGUF↓ 353

Metadata

Tags
transformers safetensors llama text-generation mergekit merge conversational base_model:hitachi-nlp/Llama-3.1-70B-FLDx2 base_model:merge:hitachi-nlp/Llama-3.1-70B-FLDx2 base_model:huihui-ai/Llama-3.3-70B-Instruct-abliterated base_model:merge:huihui-ai/Llama-3.3-70B-Instruct-abliterated text-generation-inference

Related

Other by NexesMess
Llama-3.3-Nemotron-70B-Instruct-Abliterated-TA_v0.10 25 Llama_3.3_70b_L3.3-NegativeLlama_abliterated_fusion 19
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
2025-04-10 20:50
Source huggingface.co/NexesMess/Llama_3.x_70b_FLDx2-L3.3_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 df01c2da download
model-00009-of-00030.safetensors 4.66 GB aaef08a3 download
model-00019-of-00030.safetensors 4.66 GB 33ce4c69 download
model-00024-of-00030.safetensors 4.66 GB bad63457 download
model-00014-of-00030.safetensors 4.66 GB b360c8a2 download
model-00029-of-00030.safetensors 4.66 GB 0f15e568 download
model-00003-of-00030.safetensors 4.64 GB 49f32e27 download
model-00008-of-00030.safetensors 4.64 GB 1b715661 download
model-00013-of-00030.safetensors 4.64 GB bd4bdd94 download
model-00023-of-00030.safetensors 4.64 GB fd9f0ded download
model-00028-of-00030.safetensors 4.64 GB f89eb985 download
model-00018-of-00030.safetensors 4.64 GB ceb605c9 download
model-00001-of-00030.safetensors 4.35 GB 735c7d79 download
model-00007-of-00030.safetensors 4.34 GB 1bc9ab47 download
model-00012-of-00030.safetensors 4.34 GB cb9e9264 download
model-00017-of-00030.safetensors 4.34 GB a985c4a0 download
model-00027-of-00030.safetensors 4.34 GB d64f78d1 download
model-00011-of-00030.safetensors 4.34 GB 57f4ede1 download
model-00016-of-00030.safetensors 4.34 GB d7daf1b9 download
model-00021-of-00030.safetensors 4.34 GB 58aba67b download
model-00022-of-00030.safetensors 4.34 GB 3d311ac7 download
model-00002-of-00030.safetensors 4.34 GB 6e20fa43 download
model-00006-of-00030.safetensors 4.34 GB d91c449b download
model-00026-of-00030.safetensors 4.34 GB 237e68e8 download
model-00005-of-00030.safetensors 4.33 GB aafdf1cc download
model-00015-of-00030.safetensors 4.33 GB 52752d2e download
model-00020-of-00030.safetensors 4.33 GB ed6a0892 download
model-00025-of-00030.safetensors 4.33 GB 2c00d71d download
model-00010-of-00030.safetensors 4.33 GB b5467c7d download
model-00030-of-00030.safetensors 1.86 GB 7a7696a6 download
tokenizer.json 16.4 MB da0a3059 download
model.safetensors.index.json 55.4 KB 2ef670b5 download
tokenizer_config.json 54.3 KB 8e9a45f6 download
.gitattributes 1.53 KB 52373fe2 download
README.md 1.21 KB 283f9267 download
config.json 867 B 82a450ea download
mergekit_config.yml 463 B 65e10864 download
special_tokens_map.json 444 B b8ecdee8 download

README current version from Hugging Face

base_model:

  • huihui-ai/Llama-3.3-70B-Instruct-abliterated
  • hitachi-nlp/Llama-3.1-70B-FLDx2
    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 hitachi-nlp/Llama-3.1-70B-FLDx2 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: hitachi-nlp/Llama-3.1-70B-FLDx2
    parameters:
      weight: 1.0
  - model: huihui-ai/Llama-3.3-70B-Instruct-abliterated
    parameters:
      weight: 1.0
base_model: hitachi-nlp/Llama-3.1-70B-FLDx2
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. 2025-04-10Upload folder using huggingface_hubf22256e1.2 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