Instructions to use ConwayResearch/Underdog-27B-1.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ConwayResearch/Underdog-27B-1.0 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("ConwayResearch/Underdog-27B-1.0")
config = load_config("ConwayResearch/Underdog-27B-1.0")

# 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 ConwayResearch/Underdog-27B-1.0 with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "ConwayResearch/Underdog-27B-1.0"

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": "ConwayResearch/Underdog-27B-1.0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use ConwayResearch/Underdog-27B-1.0 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 "ConwayResearch/Underdog-27B-1.0"

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 ConwayResearch/Underdog-27B-1.0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use ConwayResearch/Underdog-27B-1.0 with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "ConwayResearch/Underdog-27B-1.0"

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 "ConwayResearch/Underdog-27B-1.0" \
  --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"

Underdog-27B-1.0

Underdog-27B by Conway is a 27-billion-parameter model for conversation, writing, coding, and everyday assistance. Its MLX 4-bit QAT weights pair with Splash's speculative decoding for responsive local generation on Apple Silicon. We finetuned this model to run better in Underdog for human users, based on Qwen3.8.

Run with Splash

Install Splash 1.1.0 or later and authenticate with Hugging Face using an account with access to this repository. Then run:

hf auth login
splash serve --model ConwayResearch/Underdog-27B-1.0 --default-reasoning-effort medium

Splash automatically prepares the model and its compatible acceleration draft. Use the built-in chat interface or connect a compatible app. Medium reasoning is the recommended interactive default.

Local generation speed

Task	MLX-LM	Splash + DFlash2	Generation speedup
Email writing	33.1 tokens/s	80.6 tokens/s	2.44x
Python coding	33.0 tokens/s	130.1 tokens/s	3.94x
Long-document summarization	32.5 tokens/s	71.4 tokens/s	2.20x

Measured on an Apple M5 Max with 40 GPU cores and 48 GiB unified memory, macOS 26.5.1, using MLX 0.32.0 / MLX-LM 0.31.3 and Splash 1.1.0. Both configurations use the same MLX 4-bit weights. Values are mean decode rates from two runs per task, with temperature 0, reasoning set to none, a 512-token output budget, and no reused prompt tokens. Splash uses DFlash2 and INT8 KV; MLX-LM uses standard generation without a draft model. Engines were measured separately. Input lengths were 43, 44, and 3,003 tokens; generated output lengths may differ. Loading and warmup are excluded. Interactive medium reasoning is configured separately from these measurements.

Run with MLX

Download the complete repository and select its local directory in a compatible MLX runtime. Keep the supplied weights, tokenizer, configuration, and chat template together. The complete model download is approximately 16.08 GB; Splash manages its acceleration draft separately.

This release includes fine-tuning and quantization-aware training by Conway. The original license is preserved in LICENSE.

Downloads last month: 1,046

Safetensors

Model size

27B params

Tensor type

U32

BF16

MLX

Hardware compatibility

4-bit