qwen2.5-coder-32b-FP8-Dynamic

Qwen2.5-Coder-32B-Instruct - FP8 Dynamic Quantization

This is an FP8 quantized version of Qwen/Qwen2.5-Coder-32B-Instruct using llmcompressor with the FP8_DYNAMIC scheme.

Model Details

• Base Model: Qwen/Qwen2.5-Coder-32B-Instruct
• Quantization: FP8_DYNAMIC (W8A8)
• Format: compressed-tensors (SafeTensors)
• Memory: ~50% of original BF16 size
• Quality: <1-2% degradation on benchmarks (typical)

Quick Start

vLLM (Recommended)

pip install vllm

# Serve the model
vllm serve REPO_ID \
  --max-model-len 32768 \
  --gpu-memory-utilization 0.95

# Python API
from vllm import LLM
llm = LLM(model="REPO_ID")
outputs = llm.generate("Hello, how are you?")
print(outputs[0].outputs[0].text)

Transformers

from transformers import AutoTokenizer, AutoModelForCausalLM

model = AutoModelForCausalLM.from_pretrained(
    "REPO_ID",
    device_map="auto",
    torch_dtype="auto"
)
tokenizer = AutoTokenizer.from_pretrained("REPO_ID")

messages = [{'role': 'user', 'content': 'Hello!'}]
inputs = tokenizer.apply_chat_template(messages, return_tensors='pt').to(model.device)
outputs = model.generate(inputs, max_new_tokens=512)
print(tokenizer.decode(outputs[0]))

Quantization Details

This model was quantized using:

• Tool: llmcompressor
• Method: FP8_DYNAMIC (Round-to-Nearest)
• Targets: All Linear layers except lm_head
• Scheme: W8A8 (8-bit weights and activations)

Performance

Memory Usage

• Original BF16: ~2× size of FP8
• FP8 Quantized: ~50% of original
• Savings: ~50% VRAM reduction

Inference Speed

• Expect 1.3-1.8× faster inference vs BF16
• 2× higher throughput (more KV cache available)

Use Cases

Perfect for:

• ✅ Production inference on limited VRAM
• ✅ Running larger models on single GPU
• ✅ Cost-effective API serving
• ✅ High-throughput applications
• ✅ Extended context lengths (more KV cache)

Hardware Requirements

Minimum VRAM (approximate):

• 70B model: ~40 GB (RTX A6000, A100 40GB)
• 123B model: ~70 GB (A100 80GB, H100, H200)

Recommended:

• H100/H200 for best performance
• vLLM for optimized serving
• Enable FP8 KV cache for extended context

Important Notes

⚠️ Quantization Trade-offs:

• Slight quality degradation (typically <1-2%)
• Not suitable for fine-tuning (inference only)
• Best with vLLM (has FP8 kernel optimizations)

✅ Best Practices:

• Use --kv-cache-dtype fp8 for longer contexts
• Set --gpu-memory-utilization 0.90-0.95
• Add --enforce-eager if you encounter compilation issues

Citation

If you use this model, please cite:

@misc{model_name-fp8,
  author = {author},
  title = {model_name FP8 Dynamic Quantization},
  year = {2025},
  publisher = {HuggingFace},
  url = {https://huggingface.co/repo_id}
}

License

Inherits license from base model: Qwen/Qwen2.5-Coder-32B-Instruct

Acknowledgments

• Base model by Qwen
• Quantization via llmcompressor
• Serving optimized for vLLM

---

Want more FP8 models? Check out my other quantizations!