Instructions to use Otilde/GRMR-V3-G4B-8bit-MLX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Otilde/GRMR-V3-G4B-8bit-MLX with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm
# if on a CUDA device, also pip install mlx[cuda]

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("Otilde/GRMR-V3-G4B-8bit-MLX")

prompt = "Once upon a time in"
text = generate(model, tokenizer, prompt=prompt, verbose=True)

Transformers

How to use Otilde/GRMR-V3-G4B-8bit-MLX with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Otilde/GRMR-V3-G4B-8bit-MLX")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Otilde/GRMR-V3-G4B-8bit-MLX", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps
LM Studio

vLLM

How to use Otilde/GRMR-V3-G4B-8bit-MLX with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Otilde/GRMR-V3-G4B-8bit-MLX"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Otilde/GRMR-V3-G4B-8bit-MLX",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Otilde/GRMR-V3-G4B-8bit-MLX

SGLang

How to use Otilde/GRMR-V3-G4B-8bit-MLX with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Otilde/GRMR-V3-G4B-8bit-MLX" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Otilde/GRMR-V3-G4B-8bit-MLX",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Otilde/GRMR-V3-G4B-8bit-MLX" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Otilde/GRMR-V3-G4B-8bit-MLX",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Studio new

How to use Otilde/GRMR-V3-G4B-8bit-MLX with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Otilde/GRMR-V3-G4B-8bit-MLX to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Otilde/GRMR-V3-G4B-8bit-MLX to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Otilde/GRMR-V3-G4B-8bit-MLX to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="Otilde/GRMR-V3-G4B-8bit-MLX",
    max_seq_length=2048,
)

MLX LM

How to use Otilde/GRMR-V3-G4B-8bit-MLX with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Generate some text
mlx_lm.generate --model "Otilde/GRMR-V3-G4B-8bit-MLX" --prompt "Once upon a time"

Docker Model Runner
How to use Otilde/GRMR-V3-G4B-8bit-MLX with Docker Model Runner:
```
docker model run hf.co/Otilde/GRMR-V3-G4B-8bit-MLX
```

Otilde/GRMR-V3-G4B-8bit-MLX

This model Otilde/GRMR-V3-G4B-8bit-MLX was converted to MLX format from qingy2024/GRMR-V3-G4B using mlx-lm version 0.28.2.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("Otilde/GRMR-V3-G4B-8bit-MLX")

prompt = "hello"

if tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)