Instructions to use jsbaicenter/Aztec-Coder-4B-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jsbaicenter/Aztec-Coder-4B-NVFP4 with Transformers:

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

pipe = pipeline("text-generation", model="jsbaicenter/Aztec-Coder-4B-NVFP4")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("jsbaicenter/Aztec-Coder-4B-NVFP4")
model = AutoModelForCausalLM.from_pretrained("jsbaicenter/Aztec-Coder-4B-NVFP4", 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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use jsbaicenter/Aztec-Coder-4B-NVFP4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jsbaicenter/Aztec-Coder-4B-NVFP4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jsbaicenter/Aztec-Coder-4B-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/jsbaicenter/Aztec-Coder-4B-NVFP4

SGLang

How to use jsbaicenter/Aztec-Coder-4B-NVFP4 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 "jsbaicenter/Aztec-Coder-4B-NVFP4" \
    --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": "jsbaicenter/Aztec-Coder-4B-NVFP4",
		"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 "jsbaicenter/Aztec-Coder-4B-NVFP4" \
        --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": "jsbaicenter/Aztec-Coder-4B-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use jsbaicenter/Aztec-Coder-4B-NVFP4 with Docker Model Runner:
```
docker model run hf.co/jsbaicenter/Aztec-Coder-4B-NVFP4
```

Aztec-Coder-4B-NVFP4

File size: 4,448 Bytes

62caa4d

{
    "architectures": [
        "Qwen3_5ForCausalLM"
    ],
    "attention_bias": false,
    "attention_dropout": 0.0,
    "attn_output_gate": true,
    "bos_token_id": null,
    "dtype": "bfloat16",
    "eos_token_id": 248044,
    "full_attention_interval": 4,
    "head_dim": 256,
    "hidden_act": "silu",
    "hidden_size": 2560,
    "initializer_range": 0.02,
    "intermediate_size": 9216,
    "layer_types": [
        "linear_attention",
        "linear_attention",
        "linear_attention",
        "full_attention",
        "linear_attention",
        "linear_attention",
        "linear_attention",
        "full_attention",
        "linear_attention",
        "linear_attention",
        "linear_attention",
        "full_attention",
        "linear_attention",
        "linear_attention",
        "linear_attention",
        "full_attention",
        "linear_attention",
        "linear_attention",
        "linear_attention",
        "full_attention",
        "linear_attention",
        "linear_attention",
        "linear_attention",
        "full_attention",
        "linear_attention",
        "linear_attention",
        "linear_attention",
        "full_attention",
        "linear_attention",
        "linear_attention",
        "linear_attention",
        "full_attention"
    ],
    "linear_conv_kernel_dim": 4,
    "linear_key_head_dim": 128,
    "linear_num_key_heads": 16,
    "linear_num_value_heads": 32,
    "linear_value_head_dim": 128,
    "mamba_ssm_dtype": "float32",
    "max_position_embeddings": 262144,
    "mlp_only_layers": [],
    "model_type": "qwen3_5_text",
    "mtp_num_hidden_layers": 1,
    "mtp_use_dedicated_embeddings": false,
    "num_attention_heads": 16,
    "num_hidden_layers": 32,
    "num_key_value_heads": 4,
    "pad_token_id": null,
    "partial_rotary_factor": 0.25,
    "rms_norm_eps": 1e-06,
    "rope_parameters": {
        "mrope_interleaved": true,
        "mrope_section": [
            11,
            11,
            10
        ],
        "partial_rotary_factor": 0.25,
        "rope_theta": 10000000,
        "rope_type": "default"
    },
    "tie_word_embeddings": true,
    "transformers_version": "5.16.1",
    "use_cache": true,
    "use_mamba_kernels": true,
    "vocab_size": 248320,
    "quantization_config": {
        "config_groups": {
            "group_0": {
                "input_activations": {
                    "dynamic": false,
                    "num_bits": 4,
                    "type": "float",
                    "group_size": 16
                },
                "weights": {
                    "dynamic": false,
                    "num_bits": 4,
                    "type": "float",
                    "group_size": 16
                },
                "targets": [
                    "Linear"
                ]
            }
        },
        "ignore": [
            "lm_head",
            "model.layers.0.linear_attn*",
            "model.layers.1.linear_attn*",
            "model.layers.10.linear_attn*",
            "model.layers.11.self_attn*",
            "model.layers.12.linear_attn*",
            "model.layers.13.linear_attn*",
            "model.layers.14.linear_attn*",
            "model.layers.15.self_attn*",
            "model.layers.16.linear_attn*",
            "model.layers.17.linear_attn*",
            "model.layers.18.linear_attn*",
            "model.layers.19.self_attn*",
            "model.layers.2.linear_attn*",
            "model.layers.20.linear_attn*",
            "model.layers.21.linear_attn*",
            "model.layers.22.linear_attn*",
            "model.layers.23.self_attn*",
            "model.layers.24.linear_attn*",
            "model.layers.25.linear_attn*",
            "model.layers.26.linear_attn*",
            "model.layers.27.self_attn*",
            "model.layers.28.linear_attn*",
            "model.layers.29.linear_attn*",
            "model.layers.3.self_attn*",
            "model.layers.30.linear_attn*",
            "model.layers.31.self_attn*",
            "model.layers.4.linear_attn*",
            "model.layers.5.linear_attn*",
            "model.layers.6.linear_attn*",
            "model.layers.7.self_attn*",
            "model.layers.8.linear_attn*",
            "model.layers.9.linear_attn*"
        ],
        "quant_algo": "NVFP4",
        "producer": {
            "name": "modelopt",
            "version": "0.44.0"
        },
        "quant_method": "modelopt"
    }
}