---
type: "Article"
title: "DeepSeek-V4.1-Flash FP8/MXFP4 with SparkRing on 8× DGX Spark"
description: "DeepSeek-V4.1-Flash FP8/MXFP4 with SparkRing on 8× 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-tp8-8x-dgx-spark"
language: "en"
generated:
  by: "process:contextstudios-md/1"
  at: "2026-11-10T09:19:18.637Z"
status: "stable"
---

# DeepSeek-V4.1-Flash FP8/MXFP4 with SparkRing on 8× DGX Spark

DeepSeek-V4.1-Flash FP8/MXFP4 with SparkRing on 8× DGX Spark: 74 tok/s according to github.com (dataset as of Nov 3, 2026).

- Creator: [fujitsupolycom](https://www.contextstudios.ai/local-ai/creators/fujitsupolycom.md)
- Engine: vLLM (local-inference-lab Fork) via SparkRing (SIRCL-Collectives, switchless RDMA ueber ConnectX-7), Image Release 2026.10.2
- Quantization: Stock-Checkpoint FP8/MXFP4 (DeepSeek)
- Model family: DeepSeek-V4.1-Flash
- Hardware: dgx-spark x8
- Context: 1048576
- Artificial Analysis Intelligence Index: 39.5 ([source](https://artificialanalysis.ai/models/deepseek-v4-1-flash))

## All numbers

- 74 tok/s (Everyday; Everyday, 1 request, generation at 32K context (speed table, ring of eight), thinking on, high, with DSpark (per recipe); experimental profile) — [source](https://github.com/FujitsuPolycom/sparkring#speed)
- decode_tps: 74 (1 request) — [source](https://github.com/FujitsuPolycom/sparkring#speed)
- decode_tps: 259 (8 parallel requests) — [source](https://github.com/FujitsuPolycom/sparkring#speed)
- prefill_tps: 4851 (1 request) — [source](https://github.com/FujitsuPolycom/sparkring#speed)

## 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)