---
type: "Article"
title: "Ling-3.0-flash-VL FP8 with SGLang on 2× DGX Spark"
description: "Ling-3.0-flash-VL FP8 with SGLang on 2× DGX Spark: recipe by Weschera with speed, condition and source for every number, weights and license."
resource: "https://www.contextstudios.ai/local-ai/weschera--ling30-flash-vl-fp8-sglang-tp2-2x-dgx-spark"
language: "en"
generated:
  by: "process:contextstudios-md/1"
  at: "2026-10-02T20:14:11.470Z"
status: "stable"
---

# Ling-3.0-flash-VL FP8 with SGLang on 2× DGX Spark

Ling-3.0-flash-VL FP8 with SGLang on 2× DGX Spark: 26 tok/s according to github.com (dataset as of Sep 29, 2026).

- Creator: [Weschera](https://www.contextstudios.ai/local-ai/creators/weschera.md)
- Engine: SGLang
- Quantization: FP8 (official inclusionAI FP8-Checkpoint; ~118 GiB)
- Model family: Ling-3.0-flash-VL
- Hardware: dgx-spark x2
- Context: 131072

## All numbers

- 26 tok/s (Everyday; Everyday, 1 request, prose prompt, no speculative decoding) — [source](https://github.com/Weschera/Ling-3.0-flash-VL-2x-DGX-Sparks/blob/main/README.md)
- decode_tps: 26 (1 request) — [source](https://github.com/Weschera/Ling-3.0-flash-VL-2x-DGX-Sparks/blob/main/README.md)
- decode_tps: 32.3 (1 request) — [source](https://github.com/Weschera/Ling-3.0-flash-VL-2x-DGX-Sparks/blob/main/README.md)

## Weights

- [inclusionAI/Ling-3.0-flash-VL-fp8](https://huggingface.co/inclusionAI/Ling-3.0-flash-VL-fp8) (main, mit)

[https://github.com/Weschera/Ling-3.0-flash-VL-2x-DGX-Sparks](https://github.com/Weschera/Ling-3.0-flash-VL-2x-DGX-Sparks)

## Related

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