---
type: "Article"
title: "DeepSeek-V4-Flash-Vision-Exp 284B MXFP4 with vLLM on 2× DGX Spark"
description: "DeepSeek-V4-Flash-Vision-Exp 284B MXFP4 with vLLM on 2× DGX Spark: recipe by sfxnz with speed, condition and source for every number, weights and license."
resource: "https://www.contextstudios.ai/local-ai/sfxnz--dsv4-flash-vision-exp-1m-2x-dgx-spark"
language: "en"
generated:
  by: "process:contextstudios-md/1"
  at: "2026-10-02T21:54:17.496Z"
status: "stable"
---

# DeepSeek-V4-Flash-Vision-Exp 284B MXFP4 with vLLM on 2× DGX Spark

DeepSeek-V4-Flash-Vision-Exp 284B MXFP4 with vLLM on 2× DGX Spark: 26.2 tok/s according to github.com (dataset as of Sep 29, 2026).

- Creator: [sfxnz](https://www.contextstudios.ai/local-ai/creators/sfxnz.md)
- Engine: vLLM
- Quantization: MXFP4-Experten, FP8-Attention, fp8-KV 12-GiB-Pin, DSpark-6
- Model family: DeepSeek-V4-Flash-Vision-Exp
- Hardware: dgx-spark x2
- Context: 1048576

## All numbers

- 26.2 tok/s (Everyday; Everyday, 1 request, prose prompt, with DSpark (per recipe)) — [source](https://github.com/sfxnz/DeepSeek-V4-Flash-Vision-Exp-vLLM-2x-DGX-Spark/blob/main/README.md)
- decode_tps: 26.2 (1 request) — [source](https://github.com/sfxnz/DeepSeek-V4-Flash-Vision-Exp-vLLM-2x-DGX-Spark/blob/main/README.md)
- decode_tps: 26.2 (1 request) — [source](https://github.com/sfxnz/DeepSeek-V4-Flash-Vision-Exp-vLLM-2x-DGX-Spark/blob/main/README.md)
- prefill_tps: 2134 (1 request) — [source](https://github.com/sfxnz/DeepSeek-V4-Flash-Vision-Exp-vLLM-2x-DGX-Spark/blob/main/README.md)

## Weights

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

[https://github.com/sfxnz/DeepSeek-V4-Flash-Vision-Exp-vLLM-2x-DGX-Spark](https://github.com/sfxnz/DeepSeek-V4-Flash-Vision-Exp-vLLM-2x-DGX-Spark)

## Related

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