---
type: "Article"
title: "DeepSeek-V4.1-Flash FP8/MXFP4 with SparkRing on 4× DGX Spark"
description: "DeepSeek-V4.1-Flash FP8/MXFP4 with SparkRing on 4× DGX Spark: recipe by fujitsupolycom with speed, condition and source for every number, weights and license."
resource: "https://www.contextstudios.ai/local-ai/fujitsupolycom--deepseek-v4.1-flash-fp8-mxfp4-tp4-4x-dgx-spark"
language: "en"
generated:
  by: "process:contextstudios-md/1"
  at: "2026-10-24T16:16:26.779Z"
status: "stable"
---

# DeepSeek-V4.1-Flash FP8/MXFP4 with SparkRing on 4× DGX Spark

DeepSeek-V4.1-Flash FP8/MXFP4 with SparkRing on 4× DGX Spark: 57 tok/s according to github.com (dataset as of Sep 29, 2026).

- Creator: [fujitsupolycom](https://www.contextstudios.ai/local-ai/creators/fujitsupolycom.md)
- Engine: vLLM (local-inference-lab Fork) via SparkRing (switchless NCCL ueber ConnectX-7)
- Quantization: Stock-Checkpoint FP8/MXFP4 (DeepSeek)
- Model family: DeepSeek-V4.1-Flash
- Hardware: dgx-spark x4
- Artificial Analysis Intelligence Index: 39.5 ([source](https://artificialanalysis.ai/models/deepseek-v4-1-flash))

## All numbers

- 57 tok/s (Everyday; Everyday, 1 request, decode at 16K context (profile table), thinking on, high) — [source](https://github.com/FujitsuPolycom/sparkring#profiles)
- decode_tps: 57 (1 request) — [source](https://github.com/FujitsuPolycom/sparkring#profiles)
- decode_tps: 275 (16 parallel requests) — [source](https://github.com/FujitsuPolycom/sparkring#profiles)
- prefill_tps: 4396 (1 request) — [source](https://github.com/FujitsuPolycom/sparkring#profiles)

## Weights

- [deepseek-ai/DeepSeek-V4.1-Flash](https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash) (main, mit)

[https://github.com/FujitsuPolycom/sparkring](https://github.com/FujitsuPolycom/sparkring)

## Related

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