Instructions to use nathansutton/Ornith-1.0-35B-Q6-MLX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nathansutton/Ornith-1.0-35B-Q6-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("nathansutton/Ornith-1.0-35B-Q6-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)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use nathansutton/Ornith-1.0-35B-Q6-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 "nathansutton/Ornith-1.0-35B-Q6-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": "nathansutton/Ornith-1.0-35B-Q6-MLX"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use nathansutton/Ornith-1.0-35B-Q6-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 "nathansutton/Ornith-1.0-35B-Q6-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 nathansutton/Ornith-1.0-35B-Q6-MLX

Run Hermes

hermes

OpenClaw new

How to use nathansutton/Ornith-1.0-35B-Q6-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 "nathansutton/Ornith-1.0-35B-Q6-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 "nathansutton/Ornith-1.0-35B-Q6-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 nathansutton/Ornith-1.0-35B-Q6-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 "nathansutton/Ornith-1.0-35B-Q6-MLX"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "nathansutton/Ornith-1.0-35B-Q6-MLX"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "nathansutton/Ornith-1.0-35B-Q6-MLX",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Ornith-1.0-35B-Q6-MLX

An MLX quantization of deepreinforce-ai/Ornith-1.0-35B for running locally on Apple Silicon — a higher-bit build for big-memory Macs, used by the Terminal-Bench kit of chad, a Claude-Code-style local coding agent.

Quant

Params: 35B (MoE, 256 experts / top-8, ~3B active per token)
Scheme: uniform 6-bit group-64 affine (routers 8-bit, A_log fp32) — near-reference quality, same class as a llama.cpp Q6_K
Footprint: ~~28.5 GB weights; needs a ≥48 GB Apple Silicon Mac (~~36 GB Metal working set)
RAM: Does NOT fit 24 GB Macs — use the UD-Q2_K_XL repo there.

Use it

With chad (auto-downloads this model on first run):

uvx --from git+https://github.com/nathansutton/mlxcc chad

Or directly with mlx-lm:

from mlx_lm import load, generate
model, tok = load("nathansutton/Ornith-1.0-35B-Q6-MLX")
print(generate(model, tok, "Write a haiku about quantization.", max_tokens=64))

License

Inherits the license of the base model deepreinforce-ai/Ornith-1.0-35B. Review it before use or redistribution.

Downloads last month: 241

Safetensors

Model size

35B params

Tensor type

BF16

U32

MLX

Hardware compatibility

6-bit

Model tree for nathansutton/Ornith-1.0-35B-Q6-MLX

Base model

deepreinforce-ai/Ornith-1.0-35B

Quantized

(138)

this model