Instructions to use divinetribe/Hermes-4-14B-abliterated-4bit-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use divinetribe/Hermes-4-14B-abliterated-4bit-mlx with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("divinetribe/Hermes-4-14B-abliterated-4bit-mlx")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

HERMES

How to use divinetribe/Hermes-4-14B-abliterated-4bit-mlx with HERMES:

# No code snippets available yet for this library.

# To use this model, check the repository files and the library's documentation.

# Want to help? PRs adding snippets are welcome at:
# https://github.com/huggingface/huggingface.js

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use divinetribe/Hermes-4-14B-abliterated-4bit-mlx with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "divinetribe/Hermes-4-14B-abliterated-4bit-mlx"

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "divinetribe/Hermes-4-14B-abliterated-4bit-mlx"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use divinetribe/Hermes-4-14B-abliterated-4bit-mlx with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "divinetribe/Hermes-4-14B-abliterated-4bit-mlx"

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default divinetribe/Hermes-4-14B-abliterated-4bit-mlx

Run Hermes

hermes

OpenClaw new

How to use divinetribe/Hermes-4-14B-abliterated-4bit-mlx with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "divinetribe/Hermes-4-14B-abliterated-4bit-mlx"

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "divinetribe/Hermes-4-14B-abliterated-4bit-mlx" \
  --custom-provider-id mlx-lm \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

MLX LM

How to use divinetribe/Hermes-4-14B-abliterated-4bit-mlx with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "divinetribe/Hermes-4-14B-abliterated-4bit-mlx"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "divinetribe/Hermes-4-14B-abliterated-4bit-mlx"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "divinetribe/Hermes-4-14B-abliterated-4bit-mlx",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes-4-14B-abliterated-4bit-mlx

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-lm 0.31.2

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/

Downloads last month: 572

Safetensors

Model size

15B params

Tensor type

BF16

U32

MLX

Hardware compatibility

4-bit

Model tree for divinetribe/Hermes-4-14B-abliterated-4bit-mlx

Base model

Babsie/Hermes-4-14B-BF16-abliterated

Quantized

(1)

this model

Collection including divinetribe/Hermes-4-14B-abliterated-4bit-mlx

Abliterated MLX for Apple Silicon

Collection

Uncensored (abliterated) language models converted to MLX 4-bit for Apple Silicon — local, fast, no cloud. Companion to the claude-code-local project. • 6 items • Updated Jun 5

Paper for divinetribe/Hermes-4-14B-abliterated-4bit-mlx

Refusal in Language Models Is Mediated by a Single Direction

Paper • 2406.11717 • Published Jun 17, 2024 • 15