Instructions to use caslca/Ornith-1.0-35B-mlx-uniform-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use caslca/Ornith-1.0-35B-mlx-uniform-4bit 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("caslca/Ornith-1.0-35B-mlx-uniform-4bit")

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 caslca/Ornith-1.0-35B-mlx-uniform-4bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "caslca/Ornith-1.0-35B-mlx-uniform-4bit"

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "caslca/Ornith-1.0-35B-mlx-uniform-4bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use caslca/Ornith-1.0-35B-mlx-uniform-4bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "caslca/Ornith-1.0-35B-mlx-uniform-4bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "caslca/Ornith-1.0-35B-mlx-uniform-4bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "caslca/Ornith-1.0-35B-mlx-uniform-4bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use caslca/Ornith-1.0-35B-mlx-uniform-4bit 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 "caslca/Ornith-1.0-35B-mlx-uniform-4bit"

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 caslca/Ornith-1.0-35B-mlx-uniform-4bit

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use caslca/Ornith-1.0-35B-mlx-uniform-4bit with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "caslca/Ornith-1.0-35B-mlx-uniform-4bit"

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 "caslca/Ornith-1.0-35B-mlx-uniform-4bit" \
  --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-mlx-uniform-4bit

35B (hybrid linear-attention MoE, 256 experts / 8 active) parameters — note: Hugging Face's size badge undercounts packed 4-bit MLX weights (it counts the packed uint32 tensors), so the number shown beside this repo is wrong; the figure here is the true parameter count.

MLX uniform 4-bit (affine) quant of deepreinforce-ai/Ornith-1.0-35B (MIT).

measured	value
effective bits/weight	4.019 (measured; 80 of 512 quantized layers at 8-bit)
weights footprint	20.4 GB
quantized-layer bit histogram	8-bit: 80 · 4-bit: 432

Recommended sampling (measured, not vibes)

param	value
temperature	0.4 (certified by a per-model temperature ladder)
top_p / top_k / min_p	0.95 / 20 / 0.0
presence_penalty	0.0
max_tokens / thinking_budget	102400 / 81920 (thinking ON)

These values were certified by an execution-gated benchmark campaign (temperature ladders with convergence gates over HumanEval+/MBPP+ and agentic harnesses) — methodology and full results: https://github.com/ivan-avramov/mlx_local_stack.

Earlier revisions of this card stated ~4.649 bpw; the measured value from the serving manifest is 4.019 — corrected 2026-08-23.

Serving: MLX (mlx-lm / mlx-vlm). Quantized on-device with mlx_lm.convert (uniform) or mlx_optiq (mixed-precision KL-sensitivity recipes).

Downloads last month: 114

Safetensors

Model size

6B params

Tensor type

BF16

U32

MLX

Hardware compatibility

4-bit

Model tree for caslca/Ornith-1.0-35B-mlx-uniform-4bit

Base model

ornith-ai/Ornith-1.0-35B

Quantized

(181)

this model