Instructions to use TiGa-RCE/Bonsai-27B-MLX-BF16-Config-Repaired with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TiGa-RCE/Bonsai-27B-MLX-BF16-Config-Repaired 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("TiGa-RCE/Bonsai-27B-MLX-BF16-Config-Repaired")

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 TiGa-RCE/Bonsai-27B-MLX-BF16-Config-Repaired with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "TiGa-RCE/Bonsai-27B-MLX-BF16-Config-Repaired"

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": "TiGa-RCE/Bonsai-27B-MLX-BF16-Config-Repaired"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use TiGa-RCE/Bonsai-27B-MLX-BF16-Config-Repaired 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 "TiGa-RCE/Bonsai-27B-MLX-BF16-Config-Repaired"

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 TiGa-RCE/Bonsai-27B-MLX-BF16-Config-Repaired

Run Hermes

hermes

OpenClaw new

How to use TiGa-RCE/Bonsai-27B-MLX-BF16-Config-Repaired with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "TiGa-RCE/Bonsai-27B-MLX-BF16-Config-Repaired"

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 "TiGa-RCE/Bonsai-27B-MLX-BF16-Config-Repaired" \
  --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 TiGa-RCE/Bonsai-27B-MLX-BF16-Config-Repaired with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "TiGa-RCE/Bonsai-27B-MLX-BF16-Config-Repaired"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "TiGa-RCE/Bonsai-27B-MLX-BF16-Config-Repaired"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "TiGa-RCE/Bonsai-27B-MLX-BF16-Config-Repaired",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Bonsai-27B-MLX-BF16-Config-Repaired

File size: 784 Bytes

75d6620

# MTP Configuration Repair

The source and converted Bonsai checkpoint declare `text_config.mtp_num_hidden_layers: 1`, but neither
checkpoint's safetensors index contains an `mtp.*` weight. The oMLX MTP patch therefore constructs an
MTP module that cannot be loaded and correctly rejects calibration.

This derived baseline disables that unavailable head by setting `text_config.mtp_num_hidden_layers` to
`0`. No tensor is altered. The original converted configuration is preserved as
`config.pre-mtp-repair.json`.

- Original config SHA-256: `b0c78786138650e589131f124a1a04b2fc2c730a5ea02fd193a01f4cd0f6c928`
- Reason: source index had zero `mtp.*` tensors; conversion preserved that state.
- Scope: experiment-local derived baseline only; the Hugging Face source remains unchanged.