← back to catalog · registered 2026-11-11 12:03

groxaxo/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-EXL3-5bpw

groxaxo Deepseek 9B 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/groxaxo%2FDeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-EXL3-5bpw"
Response includes
  • classification m3
  • files 20
  • author_summary 30 models
  • readme_text full
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
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)
Refusal direction extracted via
Extraction technique

Difference-of-means

Confidence
HIGH
Why we say so
name contains 'heretic'; Heretic default extraction is difference-of-means (Arditi 2024)
Downloads · 30-day
223
Likes
1
Model age
1w ago
created 2026-11-11
Downloads over time
Now 223 → from 0 ↑ 0%
082164245 0 on Nov 11 223 on Nov 22 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.

Metadata

License
apache-2.0
Tags
exllamav3 safetensors qwen3_5 exl3 quantized text-generation conversational base_model:xtools-at/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic base_model:quantized:xtools-at/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic license:apache-2.0 5-bit region:us

Related

Total size
7.29 GB
Files
20
Quantizations
1
Registered
2026-11-11 12:03
Last updated on HF
2026-11-12 08:32

Files by quantization

Auxiliary files 20 files 7.31 GB
model-00001-of-00002.safetensors 3.92 GB a60fab16 download
model-00002-of-00002.safetensors 3.37 GB 4c430433 download
tokenizer.json 19.1 MB a5cd9732 download
vocab.json 4.99 MB b94df23d download
quantization_config.json 308 KB f3b74031 download
model.safetensors.index.json 188 KB 9fb50e0c download
UPSTREAM_README.md 37.7 KB c24c7078 download
LICENSE 11.1 KB d6456956 download
chat_template.jinja 8.53 KB 3318462a download
config.json 3.80 KB 8644cfcb download
README.md 2.47 KB aaabab11 download
.gitattributes 1.53 KB 52373fe2 download
processor_config.json 1.29 KB a9804dd9 download
conversion.json 1.19 KB 1ad12af5 download
tokenizer_config.json 1.19 KB 0bf8509e download
added_tokens.json 904 B 9955816d download
special_tokens_map.json 876 B fca0ded4 download
video_preprocessor_config.json 817 B e32b1d90 download
preprocessor_config.json 781 B 484b50c4 download
generation_config.json 142 B 79b5436a download

README current version from Hugging Face


base_model: xtools-at/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic
base_model_relation: quantized
library_name: exllamav3
license: apache-2.0
pipeline_tag: text-generation
tags:

  • exl3
  • exllamav3
  • quantized
  • qwen3_5

DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic — EXL3 5 bpw

EXL3 quantization of xtools-at/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic at revision e4bfa83c72896cbb4990c909967d6f27bb97bac4. Original weights without a LoRA adapter; the upstream tokenizer and chat template are preserved.

Quantization

Setting Value
Main linear weights 5 bits per weight target
Output head 6 bits
Vision tower 6 bits
MTP layers 4 bits
Token embeddings BF16 (16 bits)
ExLlamaV3 converter 1.6.6
Codebook mul1
Calibration Bundled corpus, 250 rows × 2048 tokens
Output scales auto
Weight files 7,826,135,525 bytes

The target bitrate applies to the main linear weights. Embeddings, the head, vision/MTP components, scales and metadata have their own storage, so the total file size is higher than a uniform 5-bit estimate.

Use

Load this folder with ExLlamaV3 1.6.6 or a compatible ExLlamaV3 backend such as TabbyAPI. Use the included original chat template. KV cache precision is a runtime setting; Q8 was used for local text-generation checks. Quantization does not change the architecture's configured context limit. Memory use depends on context length and which components are loaded.

See conversion.json for the source pin, tensor checksums and reproducible converter arguments. smoke-test.json, if present, records short deterministic text-generation checks and their context/cache settings; these are not a coding benchmark or a validation of the full context window, vision tower or MTP.

Attribution and license

Upstream model: xtools-at/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic. Upstream ancestry includes Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B. The source model card declares Apache-2.0; that license is included in LICENSE.

The upstream model card is preserved in UPSTREAM_README.md. Its training, distillation and performance statements are upstream claims, not independently established by this conversion.

README history 2 versions

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

  1. 2026-11-12 Add KL divergence, correctness and performance evaluation c76db1e 7.9 KB
    Loading...
  2. 2026-11-11 Add original-base EXL3 5 bpw quantization and provenance 8ed7d42 2.5 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