Instructions to use lmstudio-community/granite-4.0-h-tiny-MLX-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lmstudio-community/granite-4.0-h-tiny-MLX-8bit with Transformers:

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

pipe = pipeline("text-generation", model="lmstudio-community/granite-4.0-h-tiny-MLX-8bit")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("lmstudio-community/granite-4.0-h-tiny-MLX-8bit")
model = AutoModelForMultimodalLM.from_pretrained("lmstudio-community/granite-4.0-h-tiny-MLX-8bit")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

MLX

How to use lmstudio-community/granite-4.0-h-tiny-MLX-8bit 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("lmstudio-community/granite-4.0-h-tiny-MLX-8bit")

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

vLLM

How to use lmstudio-community/granite-4.0-h-tiny-MLX-8bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lmstudio-community/granite-4.0-h-tiny-MLX-8bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lmstudio-community/granite-4.0-h-tiny-MLX-8bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/lmstudio-community/granite-4.0-h-tiny-MLX-8bit

SGLang

How to use lmstudio-community/granite-4.0-h-tiny-MLX-8bit 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 "lmstudio-community/granite-4.0-h-tiny-MLX-8bit" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lmstudio-community/granite-4.0-h-tiny-MLX-8bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "lmstudio-community/granite-4.0-h-tiny-MLX-8bit" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lmstudio-community/granite-4.0-h-tiny-MLX-8bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

How to use lmstudio-community/granite-4.0-h-tiny-MLX-8bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "lmstudio-community/granite-4.0-h-tiny-MLX-8bit"

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": "lmstudio-community/granite-4.0-h-tiny-MLX-8bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use lmstudio-community/granite-4.0-h-tiny-MLX-8bit 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 "lmstudio-community/granite-4.0-h-tiny-MLX-8bit"

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 lmstudio-community/granite-4.0-h-tiny-MLX-8bit

Run Hermes

hermes

MLX LM

How to use lmstudio-community/granite-4.0-h-tiny-MLX-8bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "lmstudio-community/granite-4.0-h-tiny-MLX-8bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "lmstudio-community/granite-4.0-h-tiny-MLX-8bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "lmstudio-community/granite-4.0-h-tiny-MLX-8bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Docker Model Runner
How to use lmstudio-community/granite-4.0-h-tiny-MLX-8bit with Docker Model Runner:
```
docker model run hf.co/lmstudio-community/granite-4.0-h-tiny-MLX-8bit
```

granite-4.0-h-tiny-MLX-8bit / config.json

lmmy

Add files using upload-large-folder tool

18d3c65 verified 9 months ago

Raw

History Blame Contribute Delete

12 kB

	{
	"architectures": [
	"GraniteMoeHybridForCausalLM"
	],
	"attention_bias": false,
	"attention_dropout": 0.0,
	"attention_multiplier": 0.0078125,
	"bos_token_id": 100257,
	"embedding_multiplier": 12,
	"eos_token_id": 100257,
	"hidden_act": "silu",
	"hidden_size": 1536,
	"initializer_range": 0.1,
	"intermediate_size": 512,
	"layer_types": [
	"mamba",
	"mamba",
	"mamba",
	"mamba",
	"mamba",
	"attention",
	"mamba",
	"mamba",
	"mamba",
	"mamba",
	"mamba",
	"mamba",
	"mamba",
	"mamba",
	"mamba",
	"attention",
	"mamba",
	"mamba",
	"mamba",
	"mamba",
	"mamba",
	"mamba",
	"mamba",
	"mamba",
	"mamba",
	"attention",
	"mamba",
	"mamba",
	"mamba",
	"mamba",
	"mamba",
	"mamba",
	"mamba",
	"mamba",
	"mamba",
	"attention",
	"mamba",
	"mamba",
	"mamba",
	"mamba"
	],
	"logits_scaling": 6,
	"mamba_chunk_size": 256,
	"mamba_conv_bias": true,
	"mamba_d_conv": 4,
	"mamba_d_head": 64,
	"mamba_d_state": 128,
	"mamba_expand": 2,
	"mamba_n_groups": 1,
	"mamba_n_heads": 48,
	"mamba_proj_bias": false,
	"max_position_embeddings": 131072,
	"model_type": "granitemoehybrid",
	"normalization_function": "rmsnorm",
	"num_attention_heads": 12,
	"num_experts_per_tok": 6,
	"num_hidden_layers": 40,
	"num_key_value_heads": 4,
	"num_local_experts": 64,
	"output_router_logits": false,
	"pad_token_id": 100256,
	"position_embedding_type": "nope",
	"quantization": {
	"group_size": 64,
	"bits": 8,
	"mode": "affine",
	"model.layers.0.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.1.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.2.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.3.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.4.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.5.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.6.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.7.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.8.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.9.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.10.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.11.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.12.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.13.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.14.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.15.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.16.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.17.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.18.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.19.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.20.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.21.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.22.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.23.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.24.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.25.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.26.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.27.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.28.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.29.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.30.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.31.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.32.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.33.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.34.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.35.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.36.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.37.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.38.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.39.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	}
	},
	"quantization_config": {
	"group_size": 64,
	"bits": 8,
	"mode": "affine",
	"model.layers.0.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.1.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.2.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.3.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.4.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.5.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.6.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.7.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.8.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.9.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.10.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.11.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.12.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.13.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.14.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.15.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.16.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.17.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.18.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.19.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.20.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.21.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.22.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.23.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.24.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.25.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.26.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.27.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.28.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.29.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.30.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.31.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.32.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.33.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.34.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.35.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.36.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.37.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.38.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	},
	"model.layers.39.block_sparse_moe.router.layer": {
	"group_size": 64,
	"bits": 8
	}
	},
	"residual_multiplier": 0.22,
	"rms_norm_eps": 1e-05,
	"rope_scaling": null,
	"rope_theta": 10000,
	"router_aux_loss_coef": 0.0,
	"shared_intermediate_size": 1024,
	"tie_word_embeddings": true,
	"torch_dtype": "bfloat16",
	"transformers_version": "4.56.0",
	"use_cache": true,
	"vocab_size": 100352
	}