Instructions to use mlx-community/gemma-4-31B-it-qat-assistant-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mlx-community/gemma-4-31B-it-qat-assistant-4bit 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("mlx-community/gemma-4-31B-it-qat-assistant-4bit")

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 mlx-community/gemma-4-31B-it-qat-assistant-4bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "mlx-community/gemma-4-31B-it-qat-assistant-4bit"

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": "mlx-community/gemma-4-31B-it-qat-assistant-4bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use mlx-community/gemma-4-31B-it-qat-assistant-4bit 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 "mlx-community/gemma-4-31B-it-qat-assistant-4bit"

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 mlx-community/gemma-4-31B-it-qat-assistant-4bit

Run Hermes

hermes

MLX LM

How to use mlx-community/gemma-4-31B-it-qat-assistant-4bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "mlx-community/gemma-4-31B-it-qat-assistant-4bit"

Run an OpenAI-compatible server

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

gemma-4-31B-it-qat-assistant-4bit

This repository contains Multi-Token Prediction (MTP) drafter weights split from google/gemma-4-31B-it-qat-q4_0-unquantized-assistant for use with mlx-vlm speculative decoding.

This is not a standalone chat or text-generation model. Load it as the draft model alongside a compatible Gemma 4 31B target checkpoint.

Use with mlx-vlm

uv run mlx_vlm.generate \
  --model google/gemma-4-31B-it \
  --draft-model mlx-community/gemma-4-31B-it-qat-assistant-4bit \
  --draft-kind mtp \
  --prompt "Describe this image." \
  --max-tokens 256

For local weights:

uv run mlx_vlm.generate \
  --model /path/to/target-model \
  --draft-model /path/to/gemma-4-31B-mtp \
  --draft-kind mtp \
  --prompt "Describe this image." \
  --max-tokens 256

Model Details

Model type: gemma4_assistant
Target architecture: Gemma 4 31B
Precision: 4bit
Runtime: MLX / mlx-vlm
Format: Safetensors with MLX-compatible config and tokenizer files

The stored tensors are 4bit MLX-compatible drafter weights.

Intended Use

Use this repo only as a speculative decoding drafter for compatible Gemma 4 31B checkpoints. The target model verifies drafted tokens, while this MTP model proposes candidate tokens per decoding step.

Limitations

This checkpoint requires runtime support for Gemma 4 MTP draft models in mlx-vlm. Standard standalone generation through generic Transformers APIs is not expected to work with this repository by itself.

Please refer to the upstream google/gemma-4-31B-it model card and license terms for model usage constraints.

Downloads last month: 316

Safetensors

Model size

73.4M params

Tensor type

BF16

U32

MLX

Hardware compatibility

4-bit

Model tree for mlx-community/gemma-4-31B-it-qat-assistant-4bit

Base model

google/gemma-4-31B-it-assistant

Finetuned

google/gemma-4-31B-it-qat-q4_0-unquantized-assistant

Quantized

(14)

this model

Collection including mlx-community/gemma-4-31B-it-qat-assistant-4bit

Gemma 4 MTP QAT

Collection

40 items • Updated 4 days ago • 4