← back to catalog · registered 2026-09-15 14:56

nuoram/Ornith-1.5-35B-A3B-abliterated-W8A8

nuoram 35B MoE multimodal second-order
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
144
Likes
0
Model age
today
created 2026-09-15
Downloads over time
Now0from0↑0%
00110 on Sep 150 on Sep 16Sep
Sep 15 → Sep 16 · 2 snapshots · spans 1 day

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
Languages
en
Tags
transformers safetensors qwen3_5_moe image-text-to-text ornith abliterated uncensored w8a8 int8 compressed-tensors llm-compressor vllm

Related

Total size
0 B
Files
2
Quantizations
1
Registered
2026-09-15 14:56
Last updated on HF
2026-09-15 15:06

Files by quantization

Auxiliary files 2 files 3.61 KB
README.md 2.13 KB 819f2735 download
.gitattributes 1.48 KB a6344aac download

README current version from Hugging Face


license: apache-2.0
base_model: huihui-ai/Huihui-Ornith-1.5-35B-A3B-abliterated
base_model_relation: quantized
tags:

  • ornith
  • abliterated
  • uncensored
  • w8a8
  • int8
  • compressed-tensors
  • vllm
  • multimodal
    language:
  • en
    pipeline_tag: image-text-to-text

Ornith-1.5-35B-A3B-abliterated-W8A8

INT8 W8A8 quantisation of
huihui-ai/Huihui-Ornith-1.5-35B-A3B-abliterated,
which is an abliteration of ornith-ai/Ornith-1.5-35B-A3B.

35.7 GiB, compressed-tensors / int-quantized.

Why this one

huihui-ai's abliteration is the only one of the three that keeps the model
whole. This quantisation preserves that:

here other published W8A8
architecture Qwen3_5MoeForConditionalGeneration Qwen3_5MoeForCausalLM
model.visual.* tensors 333 0
MTP head yes yes
abliterated yes no

The two other abliterations of this model drop both the MTP head and the 333
vision tensors, and one of them also downgrades the architecture to the
text-only ForCausalLM. A text-only checkpoint silently drops every image and
OCR caller, so the vision tower is not optional.

Why W8A8 rather than FP8 or NVFP4

On Ampere (compute capability 8.6, e.g. A40), vLLM's W8A8 INT8 scheme declares a
minimum capability of 75, so the card multiplies in its own INT8 tensor cores.
FP8 W8A8 declares 89, so below Lovelace vLLM falls back to the weight-only
scheme and the activations go back to 16 bits: the memory saving is real and the
speedup is not. NVFP4 carries no native FP4 path on Ampere at all.

Serving

vllm serve nuoram/Ornith-1.5-35B-A3B-abliterated-W8A8 \
  --tensor-parallel-size 2 \
  --enable-auto-tool-choice --tool-call-parser qwen3_xml

Provenance

Quantised with llm-compressor from the bf16 checkpoint; the recipe is in
recipe.yaml in this repo. The MTP head is carried as model-mtp.safetensors.

Abliteration is by huihui-ai and the base model by ornith-ai. All credit for the
model itself belongs to them. This repo only changes the numeric format.

README history 2 versions

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

  1. 2026-09-15Model card: full lineage, quantisation scope, MTP head provenance0f335056.3 KB
    Loading...
  2. 2026-09-15Model cardd5302c42.1 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 app" button that hands off directly to a local runtime of your choice - Infrahuman, LM Studio, or Ollama. No API keys, no subscription, no prompt leakage.