Deepseek-V3-0324-W4AFP8
Model Overview
- Model Architecture: DeepseekV3ForCausalLM
- Input: Text
- Output: Text
- Model Optimizations:
- Dense Weight quantization: FP8
- MOE Weight quantization: INT4
- Activation quantization: FP8
- Release Date: 25/10/2025
- Version: 1.0
Quantized version of deepseek-ai/Deepseek-V3-0324
| Model | MMLU |
|---|---|
| novita/Deepseek-V3-0324-W4AFP8 | 0.8734 |
Model Optimizations
These models were obtained by quantizing the weights and activations of DeepSeek models to mixed-precision data types (W4(int)A(FP)8 for MoE layers and FP8 for dense layers). This optimization reduces the number of bits per parameter 4/8, significantly reducing GPU memory requirements.
Use with SGLANG
This model can be deployed efficiently using the SGLANG backend with only H200x4, as shown in the example below.
python -m sglang.launch_server --model novita/Deepseek-V3-0324-W4AFP8 --mem-fraction-static 0.85 --disable-shared-experts-fusion --tp-size 4