Modelpublic

ressl/Ornith-1.5-9B-uncensored-MLX-6bit

sourceHugging Facemitupdated 1mo agoView on Hugging Face

3likes1.4kdownloads

Model Card

[image]

Ornith-1.5-9B uncensored (MLX 6-bit)

TL;DR: abliterated Ornith-1.5-9B as 6.8 GB for Apple Silicon via mlx-lm; hard refusals reduced on the shared master from 767/1120 to 20/1120 on the cross-eval (NVFP4 sibling).

This is the MLX build of the same abliterated master used in the NVFP4 and GGUF repos. Built for security research, red-teaming and penetration-testing workflows; it will comply with requests a stock model refuses. Use responsibly.

Facts & figures


Base model	ornith-ai/Ornith-1.5-9B
Method	abliteration (3 biprojection passes) + mlx-lm conversion (6-bit)
Size	6.8 GB
Context length	262,144 tokens
Hardware used	2x NVIDIA RTX PRO 6000 Blackwell 96 GB (SM120) for ablation; Apple M5 Max 128 GB for conversion and smoke tests
Toolchain	mlx-lm 0.31.3, transformers 5.12.1

Refusal behavior (measured, hard markers only)

Effective refusal rate on 1120 harmful prompts across 5 datasets (temp 0, hard decline phrases in the first 25 words; naive keyword counts are inflated by compliant-with-disclaimer answers and are not the metric here). Measured on the NVFP4 sibling build of the identical master:

Eval set	Prompts	Baseline hard	NVFP4 hard
JailbreakBench	100	74	4
tulu-harmbench	320	165	10
HarmfulQA	300	148	2
LLM-LAT	300	284	3
mlabonne harmful	100	96	3
TOTAL	1120	767	20

Coherence of the master: GPQA-Diamond 60.1% (base model 49.5%), needle-in-haystack 1.0 at 32k/65k/131k, tool-call smoke 1.0, KL(base||ablated) median 0.324 (harmless subset 0.136).

MLX-specific validation: every quant in this ladder was generated on-device and smoke-tested (harmful-prompt compliance with zero hard-refusal markers in the first 40 words, plus math/capitals coherence checks). A full 1120-prompt cross-eval was additionally run on-device against the 4-bit build (mlxlm.server, Apple M5 Max): 74/1120 hard refusals (JailbreakBench 10/100, tulu-harmbench 10/320, HarmfulQA 3/300, LLM-LAT 37/300, mlabonne 14/100), between the NVFP4 (20) and GGUF Q4K_M (101) builds of the same master.

Run it with mlx-lm (validated locally)

bash

pip install -U mlx-lm
mlx_lm generate --model ressl/Ornith-1.5-9B-uncensored-MLX-6bit \
  --prompt "What is 17 * 23?" --max-tokens 128

Quality & limitations

—Residual hedged declines remain (20/1120 on the NVFP4 build); three ablation passes saturated.
—Quantization amplifies residual refusals on this family; the 4-bit build is the most affected. If you need the cleanest behavior, use the NVFP4 repo.
—The multimodal vision tower of the base model is not wired into these MLX builds (text only).

Provenance & reproducibility

Same master as ressl/Ornith-1.5-9B-uncensored-NVFP4: norm-preserving double Gram-Schmidt biprojection on the residual-stream writers (3 biprojection passes), converted with mlxlm.convert (qwen35 / qwen35moe support in mlx-lm 0.31.3).

License & credits

MIT (inherited from Ornith by the Ornith team, credited to ornith-ai). Abliteration, conversion and validation by Robert Ressl (Hugging Face · Website · LinkedIn · Patreon). Built with mlx-lm, NVIDIA TensorRT Model Optimizer and SGLang.

Support this work: if these models are useful to you, consider supporting on Patreon. A lot of compute and care went into this release; more at ressl.ch.