---
type: "Article"
title: "DeepSeek-V4-Flash-0731 (official checkpoint) with vLLM + DSpark on 2× DGX Spark"
description: "DeepSeek-V4-Flash-0731 (official checkpoint) with vLLM + DSpark on 2× DGX Spark: recipe by bertholomus with speed, condition and source for every number, weights and license."
resource: "https://www.contextstudios.ai/local-ai/bertholomus--deepseek-v4-flash-0731-dspark-graph8-vllm-2x-dgx-spark"
language: "en"
generated:
  by: "process:contextstudios-md/1"
  at: "2026-11-11T03:20:32.697Z"
status: "stable"
---

# DeepSeek-V4-Flash-0731 (official checkpoint) with vLLM + DSpark on 2× DGX Spark

DeepSeek-V4-Flash-0731 (official checkpoint) with vLLM + DSpark on 2× DGX Spark: 40.1 tok/s according to github.com (dataset as of Nov 3, 2026).

- Creator: [bertholomus](https://www.contextstudios.ai/local-ai/creators/bertholomus.md)
- Engine: vLLM (Image ghcr.io/anemll/dspark-vllm-gx10:0.1.1), DSpark K5, FlashInfer B12X MoE, CUDA Graphs [1, 2, 4, 8], TP2 über RoCE v2
- Quantization: offizieller Checkpoint (Revision 9e165c30), KV-Cache nvfp4_ds_mla
- Model family: DeepSeek-V4-Flash-0731
- Hardware: dgx-spark x2
- Context: 1048576
- Artificial Analysis Intelligence Index: 34.3 ([source](https://artificialanalysis.ai/models/deepseek-v4-flash))

## All numbers

- 40.1 tok/s (Everyday; Everyday, 1 request, prose prompt (temperature 0), with DSpark (per recipe)) — [source](https://github.com/bertholomus/deepseek-v4-flash-0731-dspark-graph8#initial-warm-single-request-qualification)
- decode_tps: 40.08 (1 request) — [source](https://github.com/bertholomus/deepseek-v4-flash-0731-dspark-graph8#initial-warm-single-request-qualification)
- decode_tps: 91.89 (1 request) — [source](https://github.com/bertholomus/deepseek-v4-flash-0731-dspark-graph8#initial-warm-single-request-qualification)
- ttft_ms: 235 (1 request) — [source](https://github.com/bertholomus/deepseek-v4-flash-0731-dspark-graph8#initial-warm-single-request-qualification)

## Weights

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

[https://github.com/bertholomus/deepseek-v4-flash-0731-dspark-graph8](https://github.com/bertholomus/deepseek-v4-flash-0731-dspark-graph8)

## Related

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