Instructions to use Shiftedx/ornith-1.0-35b-abliterated-mxfp4-mtplx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Shiftedx/ornith-1.0-35b-abliterated-mxfp4-mtplx 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("Shiftedx/ornith-1.0-35b-abliterated-mxfp4-mtplx")

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)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use Shiftedx/ornith-1.0-35b-abliterated-mxfp4-mtplx with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "Shiftedx/ornith-1.0-35b-abliterated-mxfp4-mtplx"

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": "Shiftedx/ornith-1.0-35b-abliterated-mxfp4-mtplx"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use Shiftedx/ornith-1.0-35b-abliterated-mxfp4-mtplx with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "Shiftedx/ornith-1.0-35b-abliterated-mxfp4-mtplx"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "Shiftedx/ornith-1.0-35b-abliterated-mxfp4-mtplx"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "Shiftedx/ornith-1.0-35b-abliterated-mxfp4-mtplx",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use Shiftedx/ornith-1.0-35b-abliterated-mxfp4-mtplx 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 "Shiftedx/ornith-1.0-35b-abliterated-mxfp4-mtplx"

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 Shiftedx/ornith-1.0-35b-abliterated-mxfp4-mtplx

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Shiftedx/ornith-1.0-35b-abliterated-mxfp4-mtplx with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "Shiftedx/ornith-1.0-35b-abliterated-mxfp4-mtplx"

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 "Shiftedx/ornith-1.0-35b-abliterated-mxfp4-mtplx" \
  --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"

Ornith 1.0 35B Abliterated MXFP4 MTPLX

Text-only MXFP4 MLX build of deepreinforce-ai/Ornith-1.0-35B, packaged for MTPLX native-MTP inference on Apple Silicon.

This is intended for local, private inference. The package contains model files only: no hosted endpoint, telemetry, prompt logs, or external service requirement.

Notes

Optimized for MTPLX MTP serving, not LM Studio indexing.
Uses a compatible prequantized q5/g64 MTP sidecar; recommended draft depth is 2.
Chat template defaults to thinking off unless enable_thinking=true is passed explicitly.
Abliteration metadata is included for transparency; no source direction file is required for inference.
Use the vision sibling when image input is required.

Local Validation

Hardware reference: Apple M4 Max Apple Silicon with 64 GB unified memory.

Check	Result
API health	Pass
Text JSON smoke	Pass
Executable code smoke	3/3
Mean decode speed	160.4 tok/s
Accepted draft ratio	93.4%

These are lightweight local checks, not public leaderboard scores.

Recommended MTPLX Settings

Use depth 2, profile sustained, tokenizer chat template, MTP enabled, and thinking disabled by default.

Downloads last month: 327

Safetensors

Model size

7B params

Tensor type

U32

BF16

MLX

Hardware compatibility

4-bit

Model tree for Shiftedx/ornith-1.0-35b-abliterated-mxfp4-mtplx

Base model

ornith-ai/Ornith-1.0-35B

Quantized

(184)

this model

Collection including Shiftedx/ornith-1.0-35b-abliterated-mxfp4-mtplx

Ornith 1.0 Apple Silicon MLX and MTPLX Builds

Collection

Local-first Ornith 1.0 MLX and MTPLX builds for Apple Silicon, including vision and abliterated variants. • 8 items • Updated 24 days ago