Instructions to use ilessio-aiflowlab/Qwen2.5-Coder-14B-Instruct-NVFP4-anima with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ilessio-aiflowlab/Qwen2.5-Coder-14B-Instruct-NVFP4-anima with Transformers:

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

pipe = pipeline("text-generation", model="ilessio-aiflowlab/Qwen2.5-Coder-14B-Instruct-NVFP4-anima")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ilessio-aiflowlab/Qwen2.5-Coder-14B-Instruct-NVFP4-anima")
model = AutoModelForCausalLM.from_pretrained("ilessio-aiflowlab/Qwen2.5-Coder-14B-Instruct-NVFP4-anima")
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 ilessio-aiflowlab/Qwen2.5-Coder-14B-Instruct-NVFP4-anima with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ilessio-aiflowlab/Qwen2.5-Coder-14B-Instruct-NVFP4-anima"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ilessio-aiflowlab/Qwen2.5-Coder-14B-Instruct-NVFP4-anima",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ilessio-aiflowlab/Qwen2.5-Coder-14B-Instruct-NVFP4-anima

SGLang

How to use ilessio-aiflowlab/Qwen2.5-Coder-14B-Instruct-NVFP4-anima 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 "ilessio-aiflowlab/Qwen2.5-Coder-14B-Instruct-NVFP4-anima" \
    --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": "ilessio-aiflowlab/Qwen2.5-Coder-14B-Instruct-NVFP4-anima",
		"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 "ilessio-aiflowlab/Qwen2.5-Coder-14B-Instruct-NVFP4-anima" \
        --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": "ilessio-aiflowlab/Qwen2.5-Coder-14B-Instruct-NVFP4-anima",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ilessio-aiflowlab/Qwen2.5-Coder-14B-Instruct-NVFP4-anima with Docker Model Runner:
```
docker model run hf.co/ilessio-aiflowlab/Qwen2.5-Coder-14B-Instruct-NVFP4-anima
```

Qwen2.5-Coder-14B-Instruct — NVFP4

4-bit (NVFP4) quantization of Qwen/Qwen2.5-Coder-14B-Instruct, produced with NVIDIA TensorRT Model Optimizer and packaged for fast inference on the NVIDIA Jetson AGX Thor (Blackwell, compute capability sm_110a).

Built with anima-thor-ui — RobotFlow Labs' open control plane + latest-vLLM image for the Jetson Thor.

✨ Why this build

~3.5× smaller than the bf16 source — fits comfortably in the Thor's 128 GB unified memory with room for a large KV cache.
Memory-bandwidth-optimal decode — NVFP4 moves ~0.55 bytes/param, roughly halving the bytes read per token versus fp8, which is what sets decode speed on bandwidth-bound edge GPUs.
Drop-in OpenAI / Anthropic serving via the anima-vllm:thor-latest engine (vLLM 0.23 · PyTorch 2.11 · CUDA 13), or any vLLM build with NVFP4 (compressed-tensors) support.

🚀 Usage (vLLM)

vllm serve ilessio-aiflowlab/Qwen2.5-Coder-14B-Instruct-NVFP4-anima \
  --trust-remote-code --attention-backend TRITON_ATTN \
  --gpu-memory-utilization 0.70 --kv-cache-dtype fp8 --max-model-len 32768

from openai import OpenAI
client = OpenAI(base_url="http://localhost:8000/v1", api_key="x")
r = client.chat.completions.create(
    model="ilessio-aiflowlab/Qwen2.5-Coder-14B-Instruct-NVFP4-anima",
    messages=[{"role": "user", "content": "Write a Python function to check if a string is a palindrome."}],
)
print(r.choices[0].message.content)

On a Jetson use --runtime nvidia (not --gpus all). The first request JIT-compiles attention (~30–60 s), then it's cached.

🔬 Quantization details


Method	NVFP4 post-training quantization (NVIDIA TensorRT Model Optimizer, `NVFP4_DEFAULT_CFG`)
Format	`compressed-tensors` (NVFP4 weights + per-group scales; fp8 KV-cache quant)
Calibration	64 diverse prompts (reasoning, code, translation, general)
Produced on	NVIDIA Jetson AGX Thor · `sm_110a` · CUDA 13 · PyTorch 2.11 · via anima-thor-ui
Base model	`Qwen/Qwen2.5-Coder-14B-Instruct`

🎯 Intended use & limitations

General-purpose inference on NVFP4-capable hardware (Blackwell and newer). Quality closely tracks the base model; as with any 4-bit PTQ, expect small deviations on the most numerically sensitive tasks. Inherits the base model's license, capabilities, biases, and intended-use terms — review the base model card. This is an independent community quantization, not affiliated with or endorsed by the base-model authors or NVIDIA.

📄 License & attribution

Released under apache-2.0 (subject to the base model's license). NVIDIA, CUDA, Jetson, and Blackwell are trademarks of NVIDIA Corporation. Quantized by RobotFlow Labs / AIFLOW LABS for the ANIMA edge-AI stack using anima-thor-ui. ⭐ the repo if this is useful.

Downloads last month: 117

Safetensors

Model size

8B params

Tensor type

BF16

F8_E4M3

Model tree for ilessio-aiflowlab/Qwen2.5-Coder-14B-Instruct-NVFP4-anima

Base model

Qwen/Qwen2.5-14B

Finetuned

Qwen/Qwen2.5-Coder-14B

Finetuned

Qwen/Qwen2.5-Coder-14B-Instruct

Quantized

(107)

this model