Instructions to use Brooooooklyn/Ornith-1.0-35B-UD-Q5_K_XL-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Brooooooklyn/Ornith-1.0-35B-UD-Q5_K_XL-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("Brooooooklyn/Ornith-1.0-35B-UD-Q5_K_XL-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 Brooooooklyn/Ornith-1.0-35B-UD-Q5_K_XL-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 "Brooooooklyn/Ornith-1.0-35B-UD-Q5_K_XL-mlx"

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": "Brooooooklyn/Ornith-1.0-35B-UD-Q5_K_XL-mlx"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use Brooooooklyn/Ornith-1.0-35B-UD-Q5_K_XL-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 "Brooooooklyn/Ornith-1.0-35B-UD-Q5_K_XL-mlx"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "Brooooooklyn/Ornith-1.0-35B-UD-Q5_K_XL-mlx"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "Brooooooklyn/Ornith-1.0-35B-UD-Q5_K_XL-mlx",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use Brooooooklyn/Ornith-1.0-35B-UD-Q5_K_XL-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 "Brooooooklyn/Ornith-1.0-35B-UD-Q5_K_XL-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 Brooooooklyn/Ornith-1.0-35B-UD-Q5_K_XL-mlx

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Brooooooklyn/Ornith-1.0-35B-UD-Q5_K_XL-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 "Brooooooklyn/Ornith-1.0-35B-UD-Q5_K_XL-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 "Brooooooklyn/Ornith-1.0-35B-UD-Q5_K_XL-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"

Brooooooklyn commited on Jun 29

Commit

31f66ac

verified ·

1 Parent(s): b697e37

Add model card

Browse files

Files changed (1) hide show

README.md +10 -10

README.md CHANGED Viewed

@@ -38,20 +38,20 @@ model_type: qwen3_5_moe
 | Repo | Format | Size | Decode (tok/s) |
 |---|---|---|---|
-| [Brooooooklyn/Ornith-1.0-35B-UD-Q3_K_XL-mlx](https://huggingface.co/Brooooooklyn/Ornith-1.0-35B-UD-Q3_K_XL-mlx) | UD-Q3_K_XL | 17 GB | 99.8 |
-| [Brooooooklyn/Ornith-1.0-35B-mxfp4-mlx](https://huggingface.co/Brooooooklyn/Ornith-1.0-35B-mxfp4-mlx) | MXFP4 | 20 GB | 45.5 |
-| [Brooooooklyn/Ornith-1.0-35B-UD-Q4_K_XL-mlx](https://huggingface.co/Brooooooklyn/Ornith-1.0-35B-UD-Q4_K_XL-mlx) | UD-Q4_K_XL | 22 GB | 98.7 |
-| [Brooooooklyn/Ornith-1.0-35B-nvfp4-mlx](https://huggingface.co/Brooooooklyn/Ornith-1.0-35B-nvfp4-mlx) | NVFP4 | 23 GB | 54.3 |
-| **[Brooooooklyn/Ornith-1.0-35B-UD-Q5_K_XL-mlx](https://huggingface.co/Brooooooklyn/Ornith-1.0-35B-UD-Q5_K_XL-mlx) (this model)** | **UD-Q5_K_XL** | **26 GB** | **95.8** |
-| [Brooooooklyn/Ornith-1.0-35B-UD-Q6_K_XL-mlx](https://huggingface.co/Brooooooklyn/Ornith-1.0-35B-UD-Q6_K_XL-mlx) | UD-Q6_K_XL | 31 GB | 93.7 |
-| [Brooooooklyn/Ornith-1.0-35B-UD-Q8_K_XL-mlx](https://huggingface.co/Brooooooklyn/Ornith-1.0-35B-UD-Q8_K_XL-mlx) | UD-Q8_K_XL | 36 GB | 92.3 |
-| [Brooooooklyn/Ornith-1.0-35B-mxfp8-mlx](https://huggingface.co/Brooooooklyn/Ornith-1.0-35B-mxfp8-mlx) | MXFP8 | 36 GB | 70.5 |
-Benchmarked on **Apple M5 Max** via [`examples/lm.ts`](https://github.com/mlx-node/mlx-node/blob/main/examples/lm.ts) (best decode tok/s across turns 2–4, steady-state, capitals chat with `reasoningEffort: 'low'`).
 ## Performance
-Steady-state decode: **95.8 tok/s** (**1.5x** vs BF16) on Apple M5 Max. Decode is memory-bandwidth bound on Apple Silicon — fewer bytes per token directly translates to higher throughput. The MoE architecture activates only 8 of 256 experts per token (~3B active out of 35.9B total), so the active-weight footprint streamed per token is what matters.
 ## Output Quality

 | Repo | Format | Size | Decode (tok/s) |
 |---|---|---|---|
+| [Brooooooklyn/Ornith-1.0-35B-UD-Q3_K_XL-mlx](https://huggingface.co/Brooooooklyn/Ornith-1.0-35B-UD-Q3_K_XL-mlx) | UD-Q3_K_XL | 17 GB | 103.8 |
+| [Brooooooklyn/Ornith-1.0-35B-mxfp4-mlx](https://huggingface.co/Brooooooklyn/Ornith-1.0-35B-mxfp4-mlx) | MXFP4 | 20 GB | 90.1 |
+| [Brooooooklyn/Ornith-1.0-35B-UD-Q4_K_XL-mlx](https://huggingface.co/Brooooooklyn/Ornith-1.0-35B-UD-Q4_K_XL-mlx) | UD-Q4_K_XL | 22 GB | 87.0 |
+| [Brooooooklyn/Ornith-1.0-35B-nvfp4-mlx](https://huggingface.co/Brooooooklyn/Ornith-1.0-35B-nvfp4-mlx) | NVFP4 | 23 GB | 87.8 |
+| **[Brooooooklyn/Ornith-1.0-35B-UD-Q5_K_XL-mlx](https://huggingface.co/Brooooooklyn/Ornith-1.0-35B-UD-Q5_K_XL-mlx) (this model)** | **UD-Q5_K_XL** | **26 GB** | **91.2** |
+| [Brooooooklyn/Ornith-1.0-35B-UD-Q6_K_XL-mlx](https://huggingface.co/Brooooooklyn/Ornith-1.0-35B-UD-Q6_K_XL-mlx) | UD-Q6_K_XL | 31 GB | 87.1 |
+| [Brooooooklyn/Ornith-1.0-35B-UD-Q8_K_XL-mlx](https://huggingface.co/Brooooooklyn/Ornith-1.0-35B-UD-Q8_K_XL-mlx) | UD-Q8_K_XL | 36 GB | 84.2 |
+| [Brooooooklyn/Ornith-1.0-35B-mxfp8-mlx](https://huggingface.co/Brooooooklyn/Ornith-1.0-35B-mxfp8-mlx) | MXFP8 | 36 GB | 80.0 |
+Benchmarked on a **cool Apple M5 Max**: median decode throughput over three 512-token generations, with a 3-minute idle cooldown before each model. (Sustained decode on Apple Silicon is thermally sensitive — back-to-back benchmarking on a hot chip can understate throughput by 20–30%, so every model here was measured from a comparable cool start.)
 ## Performance
+Steady-state decode: **91.2 tok/s** (**1.6x** vs BF16) on Apple M5 Max. Decode is memory-bandwidth bound on Apple Silicon — fewer bytes per token directly translates to higher throughput. The MoE architecture activates only 8 of 256 experts per token (~3B active out of 35.9B total), so the active-weight footprint streamed per token is what matters.
 ## Output Quality