---
type: "Article"
title: "DeepSeek-V4.1-Flash 763B EXL3 3.5 bpw with vLLM on 3× DGX Spark"
description: "DeepSeek-V4.1-Flash 763B EXL3 3.5 bpw with vLLM on 3× DGX Spark: recipe by tonyd2wild with speed, condition and source for every number, weights and license."
resource: "https://www.contextstudios.ai/local-ai/tonyd2wild--deepseek-v4.1-flash-vllm-dgx-spark-3x"
language: "en"
generated:
  by: "process:contextstudios-md/1"
  at: "2026-10-02T20:34:43.287Z"
status: "stable"
---

# DeepSeek-V4.1-Flash 763B EXL3 3.5 bpw with vLLM on 3× DGX Spark

DeepSeek-V4.1-Flash 763B EXL3 3.5 bpw with vLLM on 3× DGX Spark: 46 tok/s according to github.com (dataset as of Sep 29, 2026).

- Creator: [tonyd2wild](https://www.contextstudios.ai/local-ai/creators/tonyd2wild.md)
- Engine: vLLM
- Quantization: EXL3 3.5 bpw routed experts (Pollard) + FP8 Rest
- Model family: DeepSeek-V4.1-Flash
- Hardware: dgx-spark x3
- Context: 300000
- Artificial Analysis Intelligence Index: 39.5 ([source](https://artificialanalysis.ai/models/deepseek-v4-1-flash))

## All numbers

- 46 tok/s (Mixed; Mixed, 1 request, mixed prompt set, with DSpark (per recipe)) — [source](https://github.com/tonyd2wild/DeepSeek-V4.1-Flash-vLLM-DGX-Spark/blob/main/results/exl3tp3a11/bench-exl3tp3a11.md)
- decode_tps: 46 (1 request) — [source](https://github.com/tonyd2wild/DeepSeek-V4.1-Flash-vLLM-DGX-Spark/blob/main/results/exl3tp3a11/bench-exl3tp3a11.md)
- decode_tps: 70.05 (1 request) — [source](https://github.com/tonyd2wild/DeepSeek-V4.1-Flash-vLLM-DGX-Spark/blob/main/results/exl3tp3a11/bench-exl3tp3a11.md)
- prefill_tps: 1198.7 (1 request) — [source](https://github.com/tonyd2wild/DeepSeek-V4.1-Flash-vLLM-DGX-Spark/blob/main/results/exl3tp3a11/bench-exl3tp3a11.md)

## Weights

- [bot-lab-21/DeepSeek-V4.1-Flash-EXL3-3.5bpw-Pollard](https://huggingface.co/bot-lab-21/DeepSeek-V4.1-Flash-EXL3-3.5bpw-Pollard) (main, mit)
- [deepseek-ai/DeepSeek-V4.1-Flash](https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash) (base, mit)

[https://github.com/tonyd2wild/DeepSeek-V4.1-Flash-vLLM-DGX-Spark](https://github.com/tonyd2wild/DeepSeek-V4.1-Flash-vLLM-DGX-Spark)

## Related

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