← back to catalog · registered 2026-11-11 16:03

SargeDev/Arete-27B-Uncensored-V2-NVFP4-FP8

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/SargeDev%2FArete-27B-Uncensored-V2-NVFP4-FP8"
Response includes
  • classification m1
  • files 12
  • author_summary 16 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 · 30-day
42
Likes
1
Model age
1w ago
created 2026-11-10

Training datasets

Corpora the author lists in the model card. Datasets tracked in our /datasets catalog carry a category badge linking to the workflow stage. Others open on Hugging Face.

Downloads over time
Now 42 → from 0 ↑ 0%
0153146 0 on Nov 11 42 on Nov 22 42 on Nov 21 Nov
Nov 11 → Nov 22 · 12 snapshots · spans 11 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.

Variants by this author 3 formats · 3K downloads combined

The same weights this author released in different packaging. Pick the format that matches your runtime.

Metadata

License
apache-2.0
Tags
safetensors qwen3_5_text abliterated uncensored qwen3.8 decision nvfp4 dataset:SargeDev/jev-distill-corpus-v3 dataset:SargeDev/solar-decisions-corpus-v4 base_model:NousResearch/Arete-27B base_model:quantized:NousResearch/Arete-27B license:apache-2.0

Related

Total size
28.1 GB
Files
12
Quantizations
1
Registered
2026-11-11 16:03
Last updated on HF
2026-11-11 15:09

Files by quantization

Auxiliary files 12 files 28.1 GB
model-00001-of-00002.safetensors 18.6 GB a179785a download
model-00002-of-00002.safetensors 8.71 GB f9e35af8 download
model_mtp.safetensors 810 MB 1d8268aa download
tokenizer.json 19.1 MB f399b3cd download
model.safetensors.index.json 128 KB 35d9aa61 download
config.json 16.2 KB 457184b7 download
chat_template.jinja 8.74 KB c0c686f9 download
recipe.yaml 2.09 KB 6f8ea4ce download
.gitattributes 1.53 KB 52373fe2 download
README.md 1.50 KB f893cf8d download
tokenizer_config.json 1.32 KB 2bc99a50 download
generation_config.json 244 B 14865c33 download

README current version from Hugging Face


license: apache-2.0
datasets:

  • SargeDev/jev-distill-corpus-v3
  • SargeDev/solar-decisions-corpus-v4
    base_model: NousResearch/Arete-27B
    tags:
  • abliterated
  • uncensored
  • qwen3.8
  • decision
  • nvfp4

Arete-27B-Uncensored-V2-NVFP4-FP8

NVFP4/FP8 quantized build of Arete-27B-Uncensored-V2 — the same weights, ~29 GB instead of ~54 GB, for single-GB10 serving.

Lineage: NousResearch/Arete-27B -> OBLITERATUS aggressive abliteration -> Solar-JEV decision LoRA (solar-training-v3 checkpoint 1946, r32/alpha-64, combined 764k corpus with lm_head target) merged by direct delta arithmetic. See the V2 card for evals, decision-gate numbers, and credit.

Quant recipe (llm-compressor, proven Recipe B from our V3 line)

  • attn q/k/v/o + gate/up: NVFP4 W4A4, group 16, FP8 scales
  • down_proj: FP8 dynamic per-token
  • untouched: lm_head, embed_tokens, mtp (bf16)
  • calibration: 384 jev validation judge prompts + 128 ultrachat, MAX_SEQ 2048

Files

  • 2 bf16-scale shards + separate model_mtp.safetensors (~29 GB total)
  • recipe.yaml — the exact quant config, reproducible
  • GGUF ladder (11 quants): Arete-27B-Uncensored-V2-GGUF

Serve (vLLM, GB10)

--quantization compressed-tensors handles this format. FP8 KV cache recommended.

Credit

Nous Research (Arete base) · Pliny the Liberator (OBLITERATUS) · SargeDev (abliteration run, solar decision merge, quant, evals) · Qwen (base arch).

README history 1 version

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

  1. 2026-11-11 Upload README.md with huggingface_hub 007e625 1.5 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.

Open in Abliteration