Instructions to use mlx-community/gemma-4-12B-it-qat-assistant-nvfp4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mlx-community/gemma-4-12B-it-qat-assistant-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("mlx-community/gemma-4-12B-it-qat-assistant-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 mlx-community/gemma-4-12B-it-qat-assistant-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 "mlx-community/gemma-4-12B-it-qat-assistant-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": "mlx-community/gemma-4-12B-it-qat-assistant-nvfp4"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use mlx-community/gemma-4-12B-it-qat-assistant-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 "mlx-community/gemma-4-12B-it-qat-assistant-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 mlx-community/gemma-4-12B-it-qat-assistant-nvfp4

Run Hermes

hermes

MLX LM

How to use mlx-community/gemma-4-12B-it-qat-assistant-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 "mlx-community/gemma-4-12B-it-qat-assistant-nvfp4"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "mlx-community/gemma-4-12B-it-qat-assistant-nvfp4"
# 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-4-12B-it-qat-assistant-nvfp4",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

prince-canuma commited on 14 days ago

Commit

83f9511

verified ·

1 Parent(s): 570264b

Add MTP drafter model card

Browse files

Files changed (1) hide show

README.md +57 -7

README.md CHANGED Viewed

@@ -1,19 +1,69 @@
 ---
-language: en
 tags:
 - mlx
-library_name: mlx
-pipeline_tag: image-text-to-text
 ---
-# mlx-community/gemma-4-12B-it-qat-assistant-nvfp4
-## Use with mlx
 ```bash
-pip install -U mlx-vlm
 ```
 ```bash
-python -m mlx_vlm.generate --model mlx-community/gemma-4-12B-it-qat-assistant-nvfp4 --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>
 ```

 ---
+language:
+- en
+license: gemma
+base_model:
+- google/gemma-4-12B-it-qat-q4_0-unquantized-assistant
+library_name: mlx
+pipeline_tag: text-generation
 tags:
 - mlx
+- mlx-vlm
+- gemma4_unified_assistant
+- gemma-4
+- gemma-4-12b
+- gemma
+- mtp
+- speculative-decoding
+- draft-model
+- nvfp4
+inference: false
 ---
+# gemma-4-12B-it-qat-assistant-nvfp4
+This repository contains Multi-Token Prediction (MTP) drafter weights split from `google/gemma-4-12B-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 12B target checkpoint.
+## Use with mlx-vlm
 ```bash
+uv run mlx_vlm.generate \
+  --model google/gemma-4-12B-it \
+  --draft-model mlx-community/gemma-4-12B-it-qat-assistant-nvfp4 \
+  --draft-kind mtp \
+  --prompt "Describe this image." \
+  --max-tokens 256
 ```
+For local weights:
 ```bash
+uv run mlx_vlm.generate \
+  --model /path/to/target-model \
+  --draft-model /path/to/gemma-4-12B-mtp \
+  --draft-kind mtp \
+  --prompt "Describe this image." \
+  --max-tokens 256
 ```
+## Model Details
+- Model type: `gemma4_unified_assistant`
+- Target architecture: Gemma 4 12B
+- Precision: nvfp4
+- Runtime: MLX / `mlx-vlm`
+- Format: Safetensors with MLX-compatible config and tokenizer files
+The stored tensors are nvfp4 MLX-compatible drafter weights.
+## Intended Use
+Use this repo only as a speculative decoding drafter for compatible Gemma 4 12B 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-4-12B-it` model card and license terms for model usage constraints.