← back to catalog · registered 2026-11-14 09:03

prithivMLmods/Qwen3.5-9B-DS-v4-Flash-uncensored-heretic-NVFP4

prithivMLmods 9B multimodal 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/prithivMLmods%2FQwen3.5-9B-DS-v4-Flash-uncensored-heretic-NVFP4"
Response includes
  • classification m3
  • files 13
  • author_summary 117 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
164
Likes
1
Model age
1w ago
created 2026-11-13
Downloads over time
Now 164 → from 0 ↑ 0%
060120180 0 on Nov 14 164 on Nov 22 Nov
Nov 14 → Nov 22 · 9 snapshots · spans 8 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 4 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
Languages
en
Tags
transformers safetensors qwen3_5 image-text-to-text GPTQ mtp text-generation-inference llm-compressor vllm stable abliterated nvfp4

Related

Total size
8.72 GB
Files
13
Quantizations
1
Registered
2026-11-14 09:03
Last updated on HF
2026-11-14 07:36

Files by quantization

Auxiliary files 13 files 8.74 GB
model-00001-of-00002.safetensors 4.82 GB 8401d633 download
model-00002-of-00002.safetensors 3.44 GB b130b9ce download
model_mtp.safetensors 464 MB e9f83dae download
tokenizer.json 19.1 MB a5cd9732 download
model.safetensors.index.json 150 KB 2462f056 download
config.json 9.25 KB 89116734 download
chat_template.jinja 7.57 KB a585dec8 download
README.md 5.09 KB b5cc4746 download
.gitattributes 1.53 KB 52373fe2 download
tokenizer_config.json 1.30 KB 6d2df0d3 download
processor_config.json 1.29 KB a9804dd9 download
recipe.yaml 334 B a5b31245 download
generation_config.json 153 B 9135162c download

README current version from Hugging Face


tags:

  • GPTQ
  • qwen3_5
  • mtp
  • text-generation-inference
  • llm-compressor
  • vllm
  • stable
  • abliterated
  • nvfp4
  • nvidia
  • speculative-decoding
  • nvidia-blackwell
  • rtx-pro-6000
  • SM120
  • GB202
  • B200
  • B300
  • FP4
  • blackwell
  • Qwen3.5
  • Qwen3.6
  • Qwen3.8
  • uncensored
  • decensored
  • imatrix
    license: apache-2.0
    base_model:
  • prithivMLmods/Qwen3.5-9B-DS-v4-Flash-uncensored-heretic
    language:
  • en
    pipeline_tag: image-text-to-text
    library_name: transformers

1

Qwen3.5-9B-DS-v4-Flash-uncensored-heretic-NVFP4

Qwen3.5-9B-DS-v4-Flash-uncensored-heretic-NVFP4 is an NVFP4-quantized version of Qwen3.5-9B-DS-v4-Flash-uncensored-heretic, quantized using GPTQ (Accurate Post-Training Quantization for Generative Pre-trained Transformers). GPTQ calibration plays a critical role in stabilizing and optimizing NVFP4 compression, helping preserve accuracy close to the original weights while significantly reducing memory requirements and improving inference efficiency on NVFP4-compatible hardware.

[!NOTE]
MTP — Speculative Decoding: Yes | This is an experimental quantized release and may exhibit unexpected behaviors or reasoning artifacts in certain scenarios. Outputs should be independently evaluated.

Quantization Recipe

The model is quantized using the GPTQModifier with the NVFP4 quantization scheme.

default_stage:
  default_modifiers:
    GPTQModifier:
      targets: [Linear]
      ignore: [lm_head, "re:.*visual.*"]
      scheme: NVFP4
      weight_observer: imatrix_mse
      bypass_divisibility_checks: false
      requires_calibration_data: true
      block_size: 128
      dampening_frac: 0.01
      actorder: static
      batched_quantization: auto

Model Files

File Name File Type File Size File Link Description
chat_template.jinja Jinja Template 7.76 kB Link Chat template for formatting conversations and prompts.
config.json JSON 9.47 kB Link Core model architecture and configuration parameters.
generation_config.json JSON 153 Bytes Link Default text generation parameters (e.g., temperature, top_p).
model-00001-of-00002.safetensors Safetensors 5.18 GB Link Model weight shard 1/2. Required to load the model.
model-00002-of-00002.safetensors Safetensors 3.7 GB Link Model weight shard 2/2. Required to load the model.
model.safetensors.index.json JSON 153 kB Link Index file mapping model weights to their respective shards.
model_mtp.safetensors Safetensors 487 MB Link Multi-Token Prediction (MTP) auxiliary model weights, used to speed up generation.
processor_config.json JSON 1.33 kB Link Configuration for the multimodal processor.
recipe.yaml YAML 334 Bytes Link Configuration file detailing the quantization or training recipe (e.g., NVFP4 parameters).
tokenizer.json JSON 20 MB Link Complete tokenizer vocabulary and encoding rules.
tokenizer_config.json JSON 1.33 kB Link Tokenizer-specific configuration parameters.

License and Attribution

This model is based on and/or incorporates the following open-source projects and models:

This model is released under the Apache License 2.0.

README history 15 versions

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

  1. 2026-11-14 Update README.md e418fed 5.1 KB
    Loading...
  2. 2026-11-14 Update README.md dac05da 5.1 KB
    Loading...
  3. 2026-11-14 Update README.md cf1107f 5.1 KB
    Loading...
  4. 2026-11-14 Update README.md dbeb4e5 5.1 KB
    Loading...
  5. 2026-11-14 Update README.md 3c0e030 5.1 KB
    Loading...
  6. 2026-11-14 Update README.md d9f25ef 5.1 KB
    Loading...
  7. 2026-11-14 Update README.md df028e7 5.1 KB
    Loading...
  8. 2026-11-14 Update README.md 5161f39 5.1 KB
    Loading...
  9. 2026-11-14 Update README.md 0b0e96b 4.8 KB
    Loading...
  10. 2026-11-14 Update README.md 5f98860 4.8 KB
    Loading...
  11. 2026-11-14 Update README.md 6c1c8d8 4.7 KB
    Loading...
  12. 2026-11-13 Update README.md 6962df5 4.6 KB
    Loading...
  13. 2026-11-13 Update README.md 0385460 1.3 KB
    Loading...
  14. 2026-11-13 Update README.md fbfd824 1.3 KB
    Loading...
  15. 2026-11-13 initial commit c7fe7d3 28 B
    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