base_model: Babsie/Hermes-4-14B-BF16-abliterated
base_model_relation: quantized
license: apache-2.0
language:
- en
library_name: mlx
pipeline_tag: text-generation
tags: - abliterated
- uncensored
- hermes
- hermes-4
- qwen3
- mlx
- mlx-4bit
- apple-silicon
- on-device
- mlx-lm
- local-llm
- macbook
- 14b
- 4-bit
Hermes-4-14B-abliterated-4bit-mlx
Uncensored Hermes 4 14B, running locally on a Mac. Abliterated, quantized to 4-bit MLX for Apple Silicon — 8.3 GB, comfortable on a 16 GB Mac. No cloud, no API key, no refusals.
A 4-bit MLX quantization of Babsie/Hermes-4-14B-BF16-abliterated, tuned for fast on-device inference on Apple Silicon.
- Base model:
Babsie/Hermes-4-14B-BF16-abliterated(BF16 abliterated, ~28 GB) - Architecture: Qwen3 (Hermes 4 post-training)
- Quantization: 4-bit affine, group size 64
- Format: MLX safetensors
- Footprint: ~8 GB on disk (two safetensors shards: 5.35 GB + 2.95 GB), runs comfortably on a 16 GB Mac and flies on 32 GB+
- Context: 40,960 tokens (~40 K) — inherited unchanged from upstream Hermes 4 14B
Why this exists
Hermes 4 is NousResearch's instruction-tuned family. The 14B variant is built on Qwen3, so it inherits Qwen3's tokenizer and chat template — but the post-training is pure Hermes, which means it's tuned for tool use, structured output, and not refusing benign-but-edgy questions.
Babsie's abliteration applies refusal-direction projection (Arditi et al., 2024) to the BF16 weights. The model still has all its capabilities — it just doesn't pre-empt with a refusal on questions that the upstream Hermes would politely decline. You become the moderator.
This MLX 4-bit conversion makes it usable on Apple Silicon at the speed the hardware was designed for. 14B at 4-bit fits in ~8 GB, which means it runs even on a 16 GB MacBook — and on a 64+ GB machine you can keep multiple models loaded simultaneously.
Usage
Python (mlx-lm)
from mlx_lm import load, generate
model, tokenizer = load("divinetribe/Hermes-4-14B-abliterated-4bit-mlx")
messages = [{"role": "user", "content": "Write a haiku about local inference."}]
prompt = tokenizer.apply_chat_template(
messages, add_generation_prompt=True, tokenize=False
)
response = generate(model, tokenizer, prompt=prompt, max_tokens=256)
print(response)
Local OpenAI-compatible server
pip install mlx-lm
mlx_lm.server --model divinetribe/Hermes-4-14B-abliterated-4bit-mlx --port 8080
That gives you a local http://localhost:8080/v1/chat/completions endpoint that any OpenAI SDK client can hit. No tokens, no API bills, no telemetry.
Inside claude-code-local
MLX_MODEL=divinetribe/Hermes-4-14B-abliterated-4bit-mlx \
bash scripts/start-mlx-server.sh
This routes Claude Code (or any Anthropic-API client) to the local model. See the claude-code-local repo for the full setup.
Where it fits in the lineup
Model (all on divinetribe) |
Disk | Params | Best for |
|---|---|---|---|
Llama-3.3-70B-Instruct-abliterated-8bit-mlx |
~75 GB | 71 B | Hardest reasoning, 96 GB+ Macs |
gemma-4-31b-it-abliterated-4bit-mlx |
~16 GB | 31 B | Daily coding, 32 GB+ Macs |
Hermes-4-14B-abliterated-4bit-mlx (this) |
~8 GB | 14 B | 16 GB Macs, tool use, instruction-following |
Abliteration
"Abliteration" suppresses the model's built-in refusal direction so it doesn't refuse benign-but-edgy requests. It is not a general capability upgrade — use responsibly, and you remain bound by the upstream Hermes 4 / Qwen3 licenses.
Credits
- Hermes 4 post-training by NousResearch
- Qwen3 base by Alibaba
- Abliteration by Babsie
- MLX 4-bit conversion by divinetribe using
mlx-lm0.31.2
License
Apache 2.0, inherited from the upstream Hermes 4 / Qwen3 family.
About the author
This model was built by Matt Macosko (@nicedreamzapp) for the claude-code-local stack — run Claude Code 100% on-device with local AI on Apple Silicon (⭐ 2,664 on GitHub).
- 🤗 All my models: nicedreamzwholesale.com/software/huggingface/
- 💻 Software portfolio: nicedreamzwholesale.com/software/
- 🔒 AirGap AI (legal / healthcare / NDA workflows): nicedreamzwholesale.com/airgap/
More abliterated MLX models
Part of the Abliterated MLX for Apple Silicon
collection — 11 uncensored models converted for Macs, from Gemma 4 12B up to
Llama 3.3 70B, plus Qwen3, Qwen3-VL, Hermes 4 and Muse Glimmer 30B.
Part of Claude Code Local
This model is one of the fighters in Claude Code Local (3.2k★), which runs Claude Code 100% on-device on Apple Silicon through an MLX-native Anthropic-API server. Not sure which local model to run as an agent? Check the Agent-12 local agent leaderboard: real agent tasks, judged by the filesystem, same hardware for every row.
Built by Matt Macosko in Arcata, CA. Open to work on local-AI and Apple Silicon inference: [email protected].