---
type: "Article"
title: "DeepSeek-V4-Flash FP8 with vLLM on 2× DGX Spark (1024k context)"
description: "DeepSeek-V4-Flash FP8 with vLLM on 2× DGX Spark (1024k context): recipe by Weschera with speed, condition and source for every number, weights and license."
resource: "https://www.contextstudios.ai/local-ai/weschera--dsv4-flash-0731-dspark-k7-2x-dgx-spark"
language: "en"
generated:
  by: "process:contextstudios-md/1"
  at: "2026-10-02T21:54:33.854Z"
status: "stable"
---

# DeepSeek-V4-Flash FP8 with vLLM on 2× DGX Spark (1024k context)

DeepSeek-V4-Flash FP8 with vLLM on 2× DGX Spark (1024k context): 83.8 tok/s according to github.com (dataset as of Sep 29, 2026).

- Creator: [Weschera](https://www.contextstudios.ai/local-ai/creators/weschera.md)
- Engine: vLLM
- Quantization: Official BF16/FP8-Checkpoint mit nvfp4_ds_mla-KV (block 256); MoE FlashInfer B12X
- Model family: DeepSeek-V4-Flash
- Hardware: dgx-spark x2
- Context: 1048576

## All numbers

- 83.8 tok/s (Mixed; Mixed, 1 request, mixed prompt set, with Draft) — [source](https://github.com/Weschera/DeepSeek-V4-Flash-0731-DSpark-2x-DGX-Spark/blob/main/README.md)
- decode_tps: 83.8077 (1 request) — [source](https://github.com/Weschera/DeepSeek-V4-Flash-0731-DSpark-2x-DGX-Spark/blob/main/README.md)
- decode_tps: 83.8077 (1 request) — [source](https://github.com/Weschera/DeepSeek-V4-Flash-0731-DSpark-2x-DGX-Spark/blob/main/README.md)

## Weights

- [deepseek-ai/DeepSeek-V4-Flash-0731](https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-0731) (main, mit)

[https://github.com/Weschera/DeepSeek-V4-Flash-0731-DSpark-2x-DGX-Spark](https://github.com/Weschera/DeepSeek-V4-Flash-0731-DSpark-2x-DGX-Spark)

## Related

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