Instructions to use Irfanuruchi/qwen2.5-1.5b-buildeng-mlx-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Irfanuruchi/qwen2.5-1.5b-buildeng-mlx-8bit 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("Irfanuruchi/qwen2.5-1.5b-buildeng-mlx-8bit")

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 Irfanuruchi/qwen2.5-1.5b-buildeng-mlx-8bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "Irfanuruchi/qwen2.5-1.5b-buildeng-mlx-8bit"

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": "Irfanuruchi/qwen2.5-1.5b-buildeng-mlx-8bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use Irfanuruchi/qwen2.5-1.5b-buildeng-mlx-8bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "Irfanuruchi/qwen2.5-1.5b-buildeng-mlx-8bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "Irfanuruchi/qwen2.5-1.5b-buildeng-mlx-8bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "Irfanuruchi/qwen2.5-1.5b-buildeng-mlx-8bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use Irfanuruchi/qwen2.5-1.5b-buildeng-mlx-8bit 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 "Irfanuruchi/qwen2.5-1.5b-buildeng-mlx-8bit"

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 Irfanuruchi/qwen2.5-1.5b-buildeng-mlx-8bit

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Irfanuruchi/qwen2.5-1.5b-buildeng-mlx-8bit with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "Irfanuruchi/qwen2.5-1.5b-buildeng-mlx-8bit"

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 "Irfanuruchi/qwen2.5-1.5b-buildeng-mlx-8bit" \
  --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"

BuildEng 1.5B MLX (8-bit)

An Apple Silicon optimized version of BuildEng, a domain-specialized language model for building and structural engineering.

This repository contains the 8-bit MLX version, offering slightly higher quality than the 4-bit model while still remaining lightweight enough to run comfortably on Apple Silicon devices.

What can it help with?

Building pathology and defects
Reinforced concrete and masonry structures
Foundation and settlement issues
Structural inspections
Construction best practices
Educational support for civil and building engineering topics
General engineering Q&A

Important

BuildEng is an AI assistant and should not replace professional engineering judgment, site inspections, or licensed structural assessments.

Always verify recommendations with qualified professionals and applicable standards, regulations, and local building codes.

Base Model

Qwen2.5-1.5B-Instruct

Fine-tuned by

Irfan Uruçi

Why this version?

Higher precision than the 4-bit model
Better preservation of the original fine-tuned weights
Still small enough for everyday use on Apple Silicon devices
Ideal for users who prefer quality over maximum memory savings

Installation

pip install -U mlx-lm

Usage

from mlx_lm import load, generate

model, tokenizer = load(
    "Irfanuruchi/qwen2.5-1.5b-buildeng-mlx-8bit"
)

prompt = """
A homeowner reports diagonal cracks near a window corner.
What should be inspected first?
"""

response = generate(
    model,
    tokenizer,
    prompt=prompt,
    max_tokens=256,
)

print(response)

Example

Prompt

A homeowner reports diagonal cracks near a window corner. What should be inspected first?

Response

First determine whether the crack is active or stable, document the crack pattern and width, inspect for signs of settlement, water intrusion, and drainage issues, and evaluate whether the wall is load-bearing before considering repairs.

Other Formats

Format	Repository
Hugging Face	`Irfanuruchi/qwen2.5-1.5b-buildeng`
GGUF	`Irfanuruchi/qwen2.5-1.5b-buildeng-GGUF-Q4_K_M`
MLX 4-bit	`Irfanuruchi/qwen2.5-1.5b-buildeng-mlx-4bit`

Built by Irfan Uruchi
Computer Engineer

Downloads last month: 21

Safetensors

Model size

2B params

Tensor type

U32

F16

MLX

Hardware compatibility

8-bit

Model tree for Irfanuruchi/qwen2.5-1.5b-buildeng-mlx-8bit

Base model

Qwen/Qwen2.5-1.5B

Finetuned

Qwen/Qwen2.5-1.5B-Instruct

Quantized

(283)

this model

Irfanuruchi
/

qwen2.5-1.5b-buildeng-mlx-8bit

BuildEng 1.5B MLX (8-bit)

What can it help with?

Important

Base Model

Fine-tuned by

Why this version?

Installation

Usage

Example

Other Formats

Model tree for Irfanuruchi/qwen2.5-1.5b-buildeng-mlx-8bit

Dataset used to train Irfanuruchi/qwen2.5-1.5b-buildeng-mlx-8bit