Instructions to use TheCluster/Darwin-35B-A3B-Opus-MLX-bf16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TheCluster/Darwin-35B-A3B-Opus-MLX-bf16 with MLX:

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

from mlx_vlm import load, generate
from mlx_vlm.prompt_utils import apply_chat_template
from mlx_vlm.utils import load_config

# Load the model
model, processor = load("TheCluster/Darwin-35B-A3B-Opus-MLX-bf16")
config = load_config("TheCluster/Darwin-35B-A3B-Opus-MLX-bf16")

# Prepare input
image = ["http://images.cocodataset.org/val2017/000000039769.jpg"]
prompt = "Describe this image."

# Apply chat template
formatted_prompt = apply_chat_template(
    processor, config, prompt, num_images=1
)

# Generate output
output = generate(model, processor, formatted_prompt, image)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use TheCluster/Darwin-35B-A3B-Opus-MLX-bf16 with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "TheCluster/Darwin-35B-A3B-Opus-MLX-bf16"

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": "TheCluster/Darwin-35B-A3B-Opus-MLX-bf16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use TheCluster/Darwin-35B-A3B-Opus-MLX-bf16 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 "TheCluster/Darwin-35B-A3B-Opus-MLX-bf16"

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 TheCluster/Darwin-35B-A3B-Opus-MLX-bf16

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use TheCluster/Darwin-35B-A3B-Opus-MLX-bf16 with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "TheCluster/Darwin-35B-A3B-Opus-MLX-bf16"

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 "TheCluster/Darwin-35B-A3B-Opus-MLX-bf16" \
  --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"

Darwin-35B-A3B-Opus

Quality: original (bfloat16)

Model Specifications


Architecture	Qwen3.5 MoE (Gated DeltaNet + MoE)
Total Parameters	35B
Active Parameters	3B per forward pass
Layers	40
Layout	10 x (3 x GDN-MoE + 1 x Attention-MoE)
Experts	256 (8 routed + 1 shared active)
Context Length	262,144 native
Languages	201
Multimodal	Image and Video
License	Apache 2.0

Parent Models

Both parents share the identical Qwen3.5-35B-A3B architecture (40 layers, 256 experts, GDN+MoE hybrid). The Mother is a LoRA SFT on the same base — not a different architecture. "Text-only" refers to the training data (Claude 4.6 Opus reasoning chains), not the model structure.

Role	Model	Architecture	Training
Father	Qwen/Qwen3.5-35B-A3B	Qwen3.5-35B-A3B	Original pre-training + RLHF
Mother	Jackrong/Qwen3.5-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled	Qwen3.5-35B-A3B (same)	LoRA SFT with text-only Claude reasoning chains

Source

This model was converted to MLX format from FINAL-Bench/Darwin-35B-A3B-Opus using mlx-vlm version 0.4.4.

Downloads last month: 126

Safetensors

Model size

35B params

Tensor type

BF16

MLX

Hardware compatibility

Quantized

Model tree for TheCluster/Darwin-35B-A3B-Opus-MLX-bf16

Base model

FINAL-Bench/Darwin-35B-A3B-Opus

Finetuned

(1)

this model

Collection including TheCluster/Darwin-35B-A3B-Opus-MLX-bf16

Fine-tuned Qwen3.5 MLX

Collection

26 items • Updated Apr 16 • 6