---
type: "Article"
title: "DeepSeek-V4-Flash-0731 (official checkpoint) with vLLM + DSpark on 4× DGX Spark"
description: "DeepSeek-V4-Flash-0731 (official checkpoint) with vLLM + DSpark on 4× 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-vllm-4x-dgx-spark"
language: "en"
generated:
  by: "process:contextstudios-md/1"
  at: "2026-11-11T03:20:38.181Z"
status: "stable"
---

# DeepSeek-V4-Flash-0731 (official checkpoint) with vLLM + DSpark on 4× DGX Spark

DeepSeek-V4-Flash-0731 (official checkpoint) with vLLM + DSpark on 4× DGX Spark: 53.5 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, Image-ID sha256:3430d661…), DSpark K5, FlashInfer B12X MoE, CUDA Graphs, TP4 über Dual-Rail-RoCE v2, 8 Sequenzen / 16.384 Batched-Tokens
- Quantization: offizieller Checkpoint (Revision 9e165c30), KV-Cache nvfp4_ds_mla
- Model family: DeepSeek-V4-Flash-0731
- Hardware: dgx-spark x4
- Context: 1048576
- Artificial Analysis Intelligence Index: 34.3 ([source](https://artificialanalysis.ai/models/deepseek-v4-flash))

## All numbers

- 53.5 tok/s (Everyday; Everyday, 1 request, prose prompt (temperature 0, single run), with DSpark (per recipe)) — [source](https://github.com/bertholomus/deepseek-v4-flash-0731-dspark-graph8-4xgb10/blob/main/benchmarks/publication-smoke.json)
- decode_tps: 53.45 (1 request) — [source](https://github.com/bertholomus/deepseek-v4-flash-0731-dspark-graph8-4xgb10/blob/main/benchmarks/publication-smoke.json)
- decode_tps: 103.2 (1 request) — [source](https://github.com/bertholomus/deepseek-v4-flash-0731-dspark-graph8-4xgb10/blob/main/benchmarks/publication-smoke.json)
- ttft_ms: 181.5 (1 request) — [source](https://github.com/bertholomus/deepseek-v4-flash-0731-dspark-graph8-4xgb10/blob/main/benchmarks/publication-smoke.json)

## 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-graph8-4xgb10](https://github.com/bertholomus/deepseek-v4-flash-0731-dspark-graph8-4xgb10)

## Related

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