Instructions to use OsaurusAI/Bonsai-2-27B-1.75bit-JANG with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OsaurusAI/Bonsai-2-27B-1.75bit-JANG 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("OsaurusAI/Bonsai-2-27B-1.75bit-JANG")
config = load_config("OsaurusAI/Bonsai-2-27B-1.75bit-JANG")

# 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 OsaurusAI/Bonsai-2-27B-1.75bit-JANG with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "OsaurusAI/Bonsai-2-27B-1.75bit-JANG"

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": "OsaurusAI/Bonsai-2-27B-1.75bit-JANG"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use OsaurusAI/Bonsai-2-27B-1.75bit-JANG 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 "OsaurusAI/Bonsai-2-27B-1.75bit-JANG"

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 OsaurusAI/Bonsai-2-27B-1.75bit-JANG

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use OsaurusAI/Bonsai-2-27B-1.75bit-JANG with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "OsaurusAI/Bonsai-2-27B-1.75bit-JANG"

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 "OsaurusAI/Bonsai-2-27B-1.75bit-JANG" \
  --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"

Bonsai-2-27B-1.75bit-JANG / jang_affine_report.json

Osaurus-AI

Add Bonsai-2-27B-1.75bit-JANG

f469d00 verified 12 days ago

Raw History Blame Contribute Delete

1.7 kB

	{
	"status": "converted_not_runtime_verified",
	"profile": "JANG_AFFINE_TERNARY_PACKED",
	"storage": "ternary_packed",
	"source": "/Volumes/EricsLLMDrive/jangq-ai/sources/bonsai2-27b-20260917/Ternary-Bonsai-2-27B-mlx-2bit",
	"output": "/Users/eric/models/JANGQ-AI/Bonsai-2-27B-1.75bit-JANG",
	"counts": {
	"ternary_modules": 402,
	"vision_affine": 83,
	"passthrough": 699
	},
	"bytes_by_class": {
	"text_packed": 5877760000,
	"text_signs": 11640832,
	"text_float32": 104953856,
	"vision_packed": 251582400,
	"vision_float16": 277409248
	},
	"shifted_norms": 161,
	"text_ternary": {
	"modules": 402,
	"all_codes_in_0_1_2": true,
	"biases_equal_minus_scales": true,
	"signs_match_hadamard_json": true,
	"scale_min": 3.635883331298828e-06,
	"scale_max": 0.444580078125
	},
	"vision_rel_l1": {
	"tensor_count": 83,
	"mean": 0.02736296,
	"max": 0.04872843
	},
	"copied_auxiliary_files": [
	"hadamard.json",
	"chat_template.jinja",
	"preprocessor_config.json",
	"LICENSE",
	"NOTICE.txt",
	"generation_config.json",
	"video_preprocessor_config.json"
	],
	"stamp": {
	"bundle": "Bonsai-2-27B-1.75bit-JANG",
	"mtp": 0,
	"video": true,
	"mtp_depth": 1,
	"mtp_depth_basis": "no MTP artifact",
	"proposal_head": "stamped ineligible (native_head_already_low_bit): /Users/eric/models/JANGQ-AI/Bonsai-2-27B-1.75bit-JANG/vmlx_mtp_proposal_head.json"
	},
	"verification": {
	"status": "ok",
	"indexed_tensor_count": 2154,
	"quantized_module_count": 485,
	"hadamard_forward_modules": 401,
	"hadamard_inverse_modules": 1,
	"indexed_shard_bytes": 6523610032,
	"indexed_shard_gib": 6.076
	}
	}