Instructions to use EigenLabs/gemma-4-31B-it-qat-q4_0-MLX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use EigenLabs/gemma-4-31B-it-qat-q4_0-MLX 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("EigenLabs/gemma-4-31B-it-qat-q4_0-MLX")

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 EigenLabs/gemma-4-31B-it-qat-q4_0-MLX with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "EigenLabs/gemma-4-31B-it-qat-q4_0-MLX"

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": "EigenLabs/gemma-4-31B-it-qat-q4_0-MLX"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use EigenLabs/gemma-4-31B-it-qat-q4_0-MLX with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "EigenLabs/gemma-4-31B-it-qat-q4_0-MLX"

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 "EigenLabs/gemma-4-31B-it-qat-q4_0-MLX" \
  --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 EigenLabs/gemma-4-31B-it-qat-q4_0-MLX with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "EigenLabs/gemma-4-31B-it-qat-q4_0-MLX"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "EigenLabs/gemma-4-31B-it-qat-q4_0-MLX"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "EigenLabs/gemma-4-31B-it-qat-q4_0-MLX",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use EigenLabs/gemma-4-31B-it-qat-q4_0-MLX 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 "EigenLabs/gemma-4-31B-it-qat-q4_0-MLX"

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 EigenLabs/gemma-4-31B-it-qat-q4_0-MLX

Run Hermes

hermes

Gemma 4 31B IT — QAT q4_0, grid-faithful MLX (20 GB)

Built with Gemma. A grid-faithful MLX conversion of Google's QAT q4_0 checkpoint of Gemma 4 31B IT — the quantization grid the model was quantization-aware-trained for, emitted directly in MLX's native affine format. Runs on Apple Silicon via mlx-lm and MLX-Swift with stock kernels.

Why grid-faithful matters

Google QAT-trained these weights against the q4_0 grid (int4, group size 32, symmetric): ~53% of weights sit exactly on grid points. Re-quantizing with a generic asymmetric min-max quantizer builds a different grid and snaps those weights to the wrong points — we measured +6.3% deviation from the model Google validated. Instead, this conversion computes the q4_0 codes (d = absmax/−8, q = round(w/d)+8) and emits them as native MLX affine triplets (scales = d, biases = −8·d, gs32) — mathematically the same grid.

Measured fidelity (rel-RMS, sampled across all depths):

Reference	This artifact	Naive MLX min-max
q4_0-intended model (what Google validated)	0.135% (bf16-scale rounding only)	6.32%
BF16 QAT master	5.03% (≈ the 4.99% the QAT targets)	6.15%

Layout (mirrors Google's shipped GGUF / compressed-tensors exactly)

Tensor class	Precision
All decoder linears (q/k/v/o, gate/up/down, 60 layers)	4-bit gs32, q4_0-faithful
`embed_tokens` (tied lm_head)	6-bit gs64 (mirrors Q6_K)
Norms, QAT `layer_scalar`, rope	unquantized
Vision tower	bf16, unquantized (as Google ships it)

Benchmarks (Apple M5 Max, 40-core GPU, 614 GB/s)

Decode: ~26 tok/s single-stream (≈90% of the memory-bandwidth ceiling for a dense 31B at ~5 bpw)
Peak memory: 19.7 GB

Usage

pip install mlx-lm
python -m mlx_lm generate --model EigenLabs/gemma-4-31B-it-qat-q4_0-MLX \
  --prompt "Explain quantization-aware training in one paragraph."

Vision tensors are included with original names: text-only loaders skip them; mlx-vlm can consume them for multimodal use.

Provenance & terms

Converted from google/gemma-4-31B-it-qat-q4_0-unquantized with a deterministic, calibration-free converter (no further training). Weight values are bit-derived from Google's QAT release; use is subject to the Gemma Terms of Use. Fidelity numbers are weight-space; the conversion is designed to inherit the QAT checkpoint's validated quality by construction rather than re-evaluating it.