Instructions to use introvoyz041/granite-4.0-h-350m-mlx-4Bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use introvoyz041/granite-4.0-h-350m-mlx-4Bit with Transformers:

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

pipe = pipeline("text-generation", model="introvoyz041/granite-4.0-h-350m-mlx-4Bit")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("introvoyz041/granite-4.0-h-350m-mlx-4Bit")
model = AutoModelForCausalLM.from_pretrained("introvoyz041/granite-4.0-h-350m-mlx-4Bit", device_map="auto")
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 introvoyz041/granite-4.0-h-350m-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("introvoyz041/granite-4.0-h-350m-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

vLLM

How to use introvoyz041/granite-4.0-h-350m-mlx-4Bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "introvoyz041/granite-4.0-h-350m-mlx-4Bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "introvoyz041/granite-4.0-h-350m-mlx-4Bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/introvoyz041/granite-4.0-h-350m-mlx-4Bit

SGLang

How to use introvoyz041/granite-4.0-h-350m-mlx-4Bit 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 "introvoyz041/granite-4.0-h-350m-mlx-4Bit" \
    --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": "introvoyz041/granite-4.0-h-350m-mlx-4Bit",
		"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 "introvoyz041/granite-4.0-h-350m-mlx-4Bit" \
        --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": "introvoyz041/granite-4.0-h-350m-mlx-4Bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

How to use introvoyz041/granite-4.0-h-350m-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 "introvoyz041/granite-4.0-h-350m-mlx-4Bit"

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "introvoyz041/granite-4.0-h-350m-mlx-4Bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use introvoyz041/granite-4.0-h-350m-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 "introvoyz041/granite-4.0-h-350m-mlx-4Bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "introvoyz041/granite-4.0-h-350m-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": "introvoyz041/granite-4.0-h-350m-mlx-4Bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Docker Model Runner
How to use introvoyz041/granite-4.0-h-350m-mlx-4Bit with Docker Model Runner:
```
docker model run hf.co/introvoyz041/granite-4.0-h-350m-mlx-4Bit
```

Hermes Agent

How to use introvoyz041/granite-4.0-h-350m-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 "introvoyz041/granite-4.0-h-350m-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 introvoyz041/granite-4.0-h-350m-mlx-4Bit

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use introvoyz041/granite-4.0-h-350m-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 "introvoyz041/granite-4.0-h-350m-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 "introvoyz041/granite-4.0-h-350m-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"

introvoyz041 commited on Nov 29, 2025

Commit

11a4f48

verified ·

1 Parent(s): a399463

Upload config.json with huggingface_hub

Browse files

Files changed (1) hide show

config.json +92 -0

config.json ADDED Viewed

	@@ -0,0 +1,92 @@

+{
+    "architectures": [
+        "GraniteMoeHybridForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attention_multiplier": 0.015625,
+    "bos_token_id": 100257,
+    "embedding_multiplier": 12,
+    "eos_token_id": 100257,
+    "hidden_act": "silu",
+    "hidden_size": 768,
+    "init_method": "mup",
+    "initializer_range": 0.1,
+    "intermediate_size": 2048,
+    "layer_types": [
+        "mamba",
+        "mamba",
+        "mamba",
+        "mamba",
+        "mamba",
+        "mamba",
+        "mamba",
+        "mamba",
+        "mamba",
+        "mamba",
+        "attention",
+        "mamba",
+        "mamba",
+        "attention",
+        "mamba",
+        "mamba",
+        "mamba",
+        "attention",
+        "mamba",
+        "mamba",
+        "mamba",
+        "mamba",
+        "mamba",
+        "mamba",
+        "mamba",
+        "mamba",
+        "mamba",
+        "attention",
+        "mamba",
+        "mamba",
+        "mamba",
+        "mamba"
+    ],
+    "logits_scaling": 3,
+    "mamba_chunk_size": 256,
+    "mamba_conv_bias": true,
+    "mamba_d_conv": 4,
+    "mamba_d_head": 32,
+    "mamba_d_state": 128,
+    "mamba_expand": 2,
+    "mamba_n_groups": 1,
+    "mamba_n_heads": 48,
+    "mamba_proj_bias": false,
+    "max_position_embeddings": 32768,
+    "model_type": "granitemoehybrid",
+    "normalization_function": "rmsnorm",
+    "num_attention_heads": 12,
+    "num_experts_per_tok": 0,
+    "num_hidden_layers": 32,
+    "num_key_value_heads": 4,
+    "num_local_experts": 0,
+    "output_router_logits": false,
+    "pad_token_id": 100256,
+    "position_embedding_type": "nope",
+    "quantization": {
+        "group_size": 64,
+        "bits": 4,
+        "mode": "affine"
+    },
+    "quantization_config": {
+        "group_size": 64,
+        "bits": 4,
+        "mode": "affine"
+    },
+    "residual_multiplier": 0.246,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": null,
+    "rope_theta": 10000,
+    "router_aux_loss_coef": 0.01,
+    "shared_intermediate_size": 2048,
+    "tie_word_embeddings": true,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.56.0",
+    "use_cache": true,
+    "vocab_size": 100352
+}