---
license: mit
base_model:
- deepseek-ai/DeepSeek-V4-Flash
library_name: transformers
tags:
- compressed-tensors
- nvfp4
- vllm
---
<h1 style="display: flex; align-items: center; gap: 10px; margin: 0;">
DeepSeek-V4-Flash-NVFP4-FP8
</h1>

## Model Optimizations

This model was obtained by using the following branch with LLM Compressor: https://github.com/vllm-project/llm-compressor/pull/2647

## Deployment

This model was deployed using the following branch with vLLM: https://github.com/vllm-project/vllm/pull/41276
```bash
vllm serve RedHatAI/DeepSeek-V4-Flash-NVFP4-FP8 --tensor-parallel-size 4 --port 8089 --kv_cache_dtype="fp8"
```

## Evaluation
This model has a noticably lower accuracy recovery than the base model due to the base model being released in a quantized format and differences between mxfp4 and nvfp4.
More advanced techniques such as GPTQ can be used to increase accuracy recovery beyond this model's current state.

```bash
python tests/evals/gsm8k/gsm8k_eval.py
```

```
Results:
Accuracy: 0.910
Invalid responses: 0.000
Total latency: 173.006 s
Questions per second: 7.624
Total output tokens: 116217
Output tokens per second: 671.752
```

```bash
python3 tests/evals/mmlu_pro/mmlu_pro_eval.py --port 8089
```

```
Results:
Category: all
Accuracy: 0.554
Invalid responses: 0.000
Total latency: 112.065 s
Questions per second: 107.366
Total output tokens: 24076
Output tokens per second: 214.840
```

For more details on how this model was created and run in LLM Compressor, please contact Kyle Sayers on the vLLM Slack: https://communityinviter.com/apps/vllm-dev/join-vllm-developers-slack