Instructions to use zecanard/Gemopus-4-31B-it-MLX-4bit-nvfp4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use zecanard/Gemopus-4-31B-it-MLX-4bit-nvfp4 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("zecanard/Gemopus-4-31B-it-MLX-4bit-nvfp4")

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 zecanard/Gemopus-4-31B-it-MLX-4bit-nvfp4 with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "zecanard/Gemopus-4-31B-it-MLX-4bit-nvfp4"

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": "zecanard/Gemopus-4-31B-it-MLX-4bit-nvfp4"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use zecanard/Gemopus-4-31B-it-MLX-4bit-nvfp4 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 "zecanard/Gemopus-4-31B-it-MLX-4bit-nvfp4"

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 zecanard/Gemopus-4-31B-it-MLX-4bit-nvfp4

Run Hermes

hermes

MLX LM

How to use zecanard/Gemopus-4-31B-it-MLX-4bit-nvfp4 with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "zecanard/Gemopus-4-31B-it-MLX-4bit-nvfp4"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "zecanard/Gemopus-4-31B-it-MLX-4bit-nvfp4"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "zecanard/Gemopus-4-31B-it-MLX-4bit-nvfp4",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

🦆 zecanard/Gemopus-4-31B-it-MLX-4bit-nvfp4

This model was converted to MLX from Jackrong/Gemopus-4-31B-it using mlx-vlm version 0.4.4. Please refer to the original model card for more details.

🌟 Quality

Quantized language model with an effective 7.377 bits per weight.

mlx_vlm.convert --quantize --q-bits 4 --q-group-size 16 --q-mode nvfp4

🛠️ Customizations

This quant is aware of the current date, and also enables thinking (if available). You may disable this behavior by deleting the following line from the chat template:

{%- set enable_thinking = true %}

You may also need to adjust your environment’s Reasoning Section Parsing to recognize <|channel>thought as the Start String, and <channel|> as the End String.

🖥️ Use with `mlx`

pip install -U mlx-vlm

mlx_vlm.generate --model zecanard/Gemopus-4-31B-it-MLX-4bit-nvfp4 --max-tokens 100 --temperature 0 --prompt "Describe this image." --image <path_to_image>

Downloads last month: 90

Safetensors

Model size

9B params

Tensor type

U32

BF16

MLX

Hardware compatibility

4-bit

Model tree for zecanard/Gemopus-4-31B-it-MLX-4bit-nvfp4

Base model

google/gemma-4-31B

Finetuned

google/gemma-4-31B-it

Finetuned

Jackrong/Gemopus-4-31B-it

Quantized

(11)

this model

🦆 zecanard/Gemopus-4-31B-it-MLX-4bit-nvfp4

🌟 Quality

🛠️ Customizations

🖥️ Use with mlx

Model tree for zecanard/Gemopus-4-31B-it-MLX-4bit-nvfp4

🖥️ Use with `mlx`