Instructions to use piskle/Qwen2.5-7B-Instruct-MLX-5bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use piskle/Qwen2.5-7B-Instruct-MLX-5bit 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("piskle/Qwen2.5-7B-Instruct-MLX-5bit")

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 piskle/Qwen2.5-7B-Instruct-MLX-5bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "piskle/Qwen2.5-7B-Instruct-MLX-5bit"

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": "piskle/Qwen2.5-7B-Instruct-MLX-5bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use piskle/Qwen2.5-7B-Instruct-MLX-5bit 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 "piskle/Qwen2.5-7B-Instruct-MLX-5bit"

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 piskle/Qwen2.5-7B-Instruct-MLX-5bit

Run Hermes

hermes

MLX LM

How to use piskle/Qwen2.5-7B-Instruct-MLX-5bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "piskle/Qwen2.5-7B-Instruct-MLX-5bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "piskle/Qwen2.5-7B-Instruct-MLX-5bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "piskle/Qwen2.5-7B-Instruct-MLX-5bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Introducing the 5 bit MLX version of Qwen 2.5 7B Instruct, a 7 billion parameter dense large language model. 5 bit MLX quantization allows for a mix between precision in more advanced questions or quick answers for on-demand requests. It averages ~9tok/s and 5.5GB of RAM usage on an Apple MacBook Pro (M1, 8GB of unified memory, 256GB of internal storage).

Downloads last month: 95

Safetensors

Model size

1B params

Tensor type

BF16

U32

MLX

Hardware compatibility

5-bit

Model tree for piskle/Qwen2.5-7B-Instruct-MLX-5bit

Base model

Qwen/Qwen2.5-7B

Finetuned

Qwen/Qwen2.5-7B-Instruct

Quantized

(345)

this model