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

Libraries

How to use AtomicChat/gemma-4-31B-it-MLX-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("AtomicChat/gemma-4-31B-it-MLX-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 AtomicChat/gemma-4-31B-it-MLX-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 "AtomicChat/gemma-4-31B-it-MLX-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": "AtomicChat/gemma-4-31B-it-MLX-4bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use AtomicChat/gemma-4-31B-it-MLX-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 "AtomicChat/gemma-4-31B-it-MLX-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 AtomicChat/gemma-4-31B-it-MLX-4bit

Run Hermes

hermes

OpenClaw new

How to use AtomicChat/gemma-4-31B-it-MLX-4bit with OpenClaw:

Start the MLX server

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

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 "AtomicChat/gemma-4-31B-it-MLX-4bit" \
  --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"

MLX LM

How to use AtomicChat/gemma-4-31B-it-MLX-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 "AtomicChat/gemma-4-31B-it-MLX-4bit"

Run an OpenAI-compatible server

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

Base model: google/gemma-4-31B-it

Gemma 4 31B, self-quantized to MLX by Atomic Chat. Built straight from Google's original weights with a per-tensor importance matrix, so this is not a repack of somebody else's files. Runs fully offline.

Highlights

30.7B parameters: the weights this repo quantizes.
Context length: 256K tokens, as published by Google.
60 layers: Dense decoder, hybrid sliding-window (1024) and global attention.
Modalities: Text, Image.
Full imatrix ladder: every quant is calibrated with an importance matrix.
Reasoning: All models in the family are designed as highly capable reasoners, with configurable thinking modes.
Diverse & Efficient Architectures: Offers Dense and Mixture-of-Experts (MoE) variants of different sizes for scalable deployment.

These MLXs are self-quantized from the original weights, not a repack. The importance matrix keeps low-bit quants closer to the full-precision model.

Model Overview

Property	Value
Base model	`google/gemma-4-31B-it`
Parameters	30.7B
Layers	60
Sliding window	1024 tokens
Context length	256K tokens
Vocabulary	262K
Modalities	Text, Image
Architecture	Dense decoder, hybrid sliding-window (1024) and global attention, 32 attention heads over 16 KV heads, `Gemma4ForConditionalGeneration`
This repo	MLX weights

Benchmarks

Benchmark	Score
MMLU Pro	85.2%
AIME 2026 no tools	89.2%
LiveCodeBench v6	80.0%
Codeforces ELO	2150
GPQA Diamond	84.3%
Tau2 (average over 3)	76.9%
HLE no tools	19.5%
HLE with search	26.5%
BigBench Extra Hard	74.4%
MMMLU	88.4%
MMMU Pro	76.9%
OmniDocBench 1.5 (average edit distance, lower is better)	0.131
MATH-Vision	85.6%
MedXPertQA MM	61.3%
MRCR v2 8 needle 128k (average)	66.4%

Scores are Google's published results for the base google/gemma-4-31B-it, not our own measurements. Quantization preserves the large majority of this; Q4_K_M and up stay close to full precision.

Get started

Atomic Chat: search AtomicChat/gemma-4-31B-it-MLX-4bit and hit Use this model.
mlx-lm: mlx_lm.generate --model AtomicChat/gemma-4-31B-it-MLX-4bit --prompt "Hello" --max-tokens 512
Server: mlx_lm.server --model AtomicChat/gemma-4-31B-it-MLX-4bit --port 8080

Best practices

Parameter	Value
temperature	1.0
top_p	0.95
top_k	64

Google's recommended sampling configuration for google/gemma-4-31B-it.

How these were made

Download google/gemma-4-31B-it (original weights).
Convert and quantize with mlx_lm.convert on our pipeline.

License

Original model by Google, released under the Apache 2.0 license. Full terms: Apache 2.0. Quantized by Atomic Chat.

Downloads last month: 708

Safetensors

Model size

31B params

Tensor type

BF16

U32

MLX

Hardware compatibility

4-bit

Model tree for AtomicChat/gemma-4-31B-it-MLX-4bit

Base model

google/gemma-4-31B

Finetuned

google/gemma-4-31B-it

Quantized

(284)

this model

Collection including AtomicChat/gemma-4-31B-it-MLX-4bit

Gemma 4

Collection

Atomic Chat GGUF builds of Google Gemma 4 • 20 items • Updated about 23 hours ago • 1