---
type: "Article"
title: "DeepSeek-V4-Flash 305B FP8 with vLLM on 3× DGX Spark"
description: "DeepSeek-V4-Flash 305B FP8 with vLLM on 3× DGX Spark: recipe by MiaAI-Lab with speed, condition and source for every number, weights and license."
resource: "https://www.contextstudios.ai/local-ai/miaai-lab--deepseek-v4-flash-dspark-2x-dgx-spark-3x"
language: "en"
generated:
  by: "process:contextstudios-md/1"
  at: "2026-10-02T23:16:06.680Z"
status: "stable"
---

# DeepSeek-V4-Flash 305B FP8 with vLLM on 3× DGX Spark

DeepSeek-V4-Flash 305B FP8 with vLLM on 3× DGX Spark: 41.9 tok/s according to github.com (dataset as of Sep 29, 2026).

- Creator: [MiaAI-Lab](https://www.contextstudios.ai/local-ai/creators/miaai-lab.md)
- Engine: vLLM ghcr.io/anemll/dspark-vllm-gx10:0.1.1
- Quantization: Original-Checkpoint (FP8/FP4) , TP3-Head-Pad 64→72
- Model family: DeepSeek-V4-Flash
- Hardware: dgx-spark x3
- Context: 1048576

## All numbers

- 41.9 tok/s (Everyday; Everyday, 1 request, prose prompt, with DSpark (per recipe)) — [source](https://github.com/MiaAI-Lab/DeepSeek-v4-Flash-DSpark-2x-DGX-Spark/blob/main/docs/TP3.md#L123)
- decode_tps: 41.9 (1 request) — [source](https://github.com/MiaAI-Lab/DeepSeek-v4-Flash-DSpark-2x-DGX-Spark/blob/main/docs/TP3.md#L123)
- decode_tps: 41.9 (1 request) — [source](https://github.com/MiaAI-Lab/DeepSeek-v4-Flash-DSpark-2x-DGX-Spark/blob/main/docs/TP3.md#L123)

## Weights

- [deepseek-ai/DeepSeek-V4-Flash-Vision-Exp](https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-Vision-Exp) (main, mit)

[https://github.com/MiaAI-Lab/DeepSeek-v4-Flash-DSpark-2x-DGX-Spark](https://github.com/MiaAI-Lab/DeepSeek-v4-Flash-DSpark-2x-DGX-Spark)

## Related

- [Local AI on your hardware.](https://www.contextstudios.ai/local-ai.md)