Instructions to use TiGa-RCE/Bonsai-27B-oQ2e-S32-Smoke with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TiGa-RCE/Bonsai-27B-oQ2e-S32-Smoke 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-oQ2e-S32-Smoke")

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-oQ2e-S32-Smoke 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-oQ2e-S32-Smoke"

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-oQ2e-S32-Smoke"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use TiGa-RCE/Bonsai-27B-oQ2e-S32-Smoke 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-oQ2e-S32-Smoke"

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-oQ2e-S32-Smoke

Run Hermes

hermes

OpenClaw new

How to use TiGa-RCE/Bonsai-27B-oQ2e-S32-Smoke 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-oQ2e-S32-Smoke"

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-oQ2e-S32-Smoke" \
  --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-oQ2e-S32-Smoke 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-oQ2e-S32-Smoke"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "TiGa-RCE/Bonsai-27B-oQ2e-S32-Smoke"
# 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-oQ2e-S32-Smoke",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Bonsai 27B oQ2e S32 Calibration Smoke

Experimental calibration artifact. Not a quality release. Do not use this model to judge Bonsai quality or as a production checkpoint.

This repository preserves the first bounded oQe 2-bit output that loaded and generated normally on a 32 GB Apple Silicon host. Its purpose is reproducible pipeline evidence and storage, not a recommended deployment target.

What this proves

An oQe-enhanced 2-bit MLX artifact could be produced from the public BF16 conversion baseline and loaded by the local oMLX runtime.
The 32-sample calibration completed with 496 imatrix entries.
On fixed 10-question smoke screens it scored HellaSwag 7/10 and ARC-Challenge 6/10.
Single-request oMLX generation measured 15.71 tok/s at a 1,024-token prompt and 15.44 tok/s at 4,096 tokens, with cache disabled.

What this does not prove

The sensitivity stage was intentionally minimal: 2 samples of 64 tokens. The artifact has not passed the predeclared 100-question evaluations or a quality-sized sensitivity pass. It must not be compared with a validated Q4, Q8, oQ4, or oQ8 checkpoint as though it were a quality result.

Reproduction Parameters

Setting	Value
oQ level	2
imatrix samples	32
imatrix sequence length	512
sensitivity samples	2
sensitivity sequence length	64
calibration dataset	`oqe_code_multilingual`
imatrix entries	496

oq_imatrix_report.json, PROVENANCE.json, and the included IMATRIX_CACHE_SHA256.npz record the exact emitted artifact and calibration evidence. The NPZ is archival provenance; it is not needed to run the model.

Provenance

Derived baseline: TiGa-RCE/Bonsai-27B-MLX-BF16-Config-Repaired
Original source: prism-ml/Bonsai-27B-gguf
Source revision: 0cf7e3d21581b169b4df1de8bf01316000e2fbb7
Original source file SHA-256: d4a381a6d07131c34af888607bdbda49fc885c97673a0d22aa3e0f0284bba566
Output model hash manifest: MODEL_SHA256SUMS.txt

The project retains the upstream Apache-2.0 LICENSE.txt and NOTICE.txt.

Attribution

Created by Technologies Brewster Jennings du Canada for the Bonsai MLX quantization experiment. Created using Bonsai by Prism ML, derived from Qwen3.6-27B.