Get the app
← back to catalog · registered 2026-09-02 19:03

esatapedico/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU-NVFP4

esatapedico 19B 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/esatapedico%2FQwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU-NVFP4"
Response includes
  • classification m3
  • files 9
  • hub_downloads_all_time 1,037
  • author_summary 10 models
  • readme_text full
Try next
GET/models?author=esatapedico
All 10 models by esatapedico
 GET/methods/m3
What "m3" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M3
Primary method

Layer-wise ablation

Applied on top of direct removal inherited from the base model.
Confidence
HIGH
Inherited from base model
M1 Direct removal →
Why this label 2 signals
Producer identity confirmed by naming conventions, tags or the model card. This label is very unlikely to change.
  • 'heretic' in model name (Heretic-produced)
  • Heretic uses layer-wise optimization (M3) with underlying direction removal (M1)
How we label → About M3 →
Refusal direction extracted via
Extraction technique

Difference-of-means

FromArditi et al. (2024) ↗
Confidence
HIGH
Why we say so
name contains 'heretic'; Heretic default extraction is difference-of-means (Arditi 2024)
What is a refusal direction? → Read the paper ↗
Downloads · lifetime
1K
597 last 30d - active
Likes
5
Model age
8w ago
created 2026-09-02
Downloads over time
Now1.6K→from0↑0%
06041.2K1.8K0 on Sep 21.6K on Oct 29SepOct
Sep 2 → Oct 29 · 58 snapshots · spans 57 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.

DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU↓ 14,771 this lineage
esatapedico/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU-NVFP4↓ 597

Variants by this author 2 formats · 5K downloads combined

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

Metadata

License
apache-2.0
Languages
en multilingual
Tags
transformers safetensors qwen3_5_text text-generation nvfp4 qwen3.8 qwen3.5 blackwell mtp speculative-decoding turbo fable

Related

Other by esatapedico
Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored-NVFP4-GGUF 7K Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU-NVFP4-GGUF 5K Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP-NVFP4-GGUF 1K Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU-NVFP4-BUDGET-GGUF 729 Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored-NVFP4-BUDGET-GGUF 636
Same base model
DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF 1.7M DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored-NM-DAU-NEO-MTP-GGUF 51K Solstice-AI/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU-AWQ 9K Solstice-AI/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU-mlx-oQ8e-1M 8K Solstice-AI/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-GGUF-UltraOptimised-DSpark 8K
Total size
25.7 GB
Files
9
Quantizations
1
Registered
2026-09-02 19:03
Last updated on HF
2026-10-16 20:27
Source huggingface.co/esatapedico/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU-NVFP4 ↗ Base model DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU →

Files by quantization

Auxiliary files 9 files 25.8 GB
model.safetensors 25.7 GB 72c92e78 download
tokenizer.json 19.1 MB 87a7830d download
config.json 14.7 KB 15ba9043 download
chat_template.jinja 8.74 KB 5a39aa2b download
README.md 2.55 KB c3a5bfde download
.gitattributes 1.53 KB 52373fe2 download
tokenizer_config.json 1.17 KB 4d9ac0cf download
generation_config.json 213 B 79c8cce3 download
recipe.yaml 212 B 6cb52593 download

README current version from Hugging Face

license: apache-2.0
base_model: DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU
pipeline_tag: text-generation
library_name: transformers
tags:

  • nvfp4
  • qwen3.8
  • qwen3.5
  • blackwell
  • mtp
  • speculative-decoding
  • turbo
  • fable
  • cold-fusion
  • compressed-tensors
    language:
  • en
  • multilingual
    quantization_config:
    quant_method: compressed-tensors
    format: nvfp4-pack-quantized

Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU-NVFP4

NVFP4 checkpoint of DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU. NVFP4 here means W4A16 with FP8 scales, group size 16, weight only. Linear layers are NVFP4, vision tower, linear attention path, lm_head and MTP head are kept in BF16 at the source. No calibration data was used. This matches the pattern used for other Qwen3.8 Cold Fusion NVFP4 builds.

HF repo: esatapedico/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU-NVFP4
GGUF family: esatapedico/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU-NVFP4-GGUF (6 tiers, see the GGUF model card)

At a glance

Field Value
Format compressed-tensors nvfp4-pack-quantized
Quantization W4A16, group size 16, FP8 E4M3 scales, weight only
Kept in BF16 vision tower, linear attention path, lm_head, embeddings, MTP head
Calibration none
Base DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU (Qwen3.8-27B, Apache 2.0)

Quantized set covers MLP on all 64 layers plus Q, K, V, O on the 16 full attention layers. The DeltaNet path stays BF16 in this checkpoint and is normalized to NVFP4 in the GGUF tier builds (448 tensor backbone).

Checkpoint

  • Single model.safetensors about 26 GB
  • config.json quantization_config.format=nvfp4-pack-quantized, quant_method=compressed-tensors, Qwen3_5ForCausalLM, 64 layers, hybrid GatedDeltaNet, 262144 context, MTP head
  • tokenizer.json intact, chat template intact
  • NVFP4 tensors verified via metadata checks

Provenance

Derivative of DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU (Apache 2.0) which itself derives from Qwen/Qwen3.8-27B. See the GGUF model card for full attribution. This checkpoint is the source for the GGUF family, which contains 1,122 tensors per file with a shared 448 tensor NVFP4 backbone.

License

apache-2.0

Card written with AI assistance.

README history 2 versions

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

  1. 2026-10-16Upload README.md with huggingface_hubc81c4583 KB
    Loading...
  2. 2026-09-02Upload folder using huggingface_hube6f0f6a2.6 KB
    Loading...

Discussions 1 thread

  1. 2026-09-07Is it possible to create an artifact similar in scale to Unsloft's NVFP4 versio…open8 💬#1
    Loading...

Continue on Hugging Face →

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