---
type: "Article"
title: "GLM-5.3-Flash NVFP4 with vLLM on 2× DGX Spark (128k context, with MTP)"
description: "GLM-5.3-Flash NVFP4 with vLLM on 2× DGX Spark (128k context, with MTP): recipe by Weschera with speed, condition and source for every number, weights and license."
resource: "https://www.contextstudios.ai/local-ai/weschera--glm53-flash-nvfp4-vcruz-mtp4-2x-dgx-spark"
language: "en"
generated:
  by: "process:contextstudios-md/1"
  at: "2026-10-02T21:57:35.920Z"
status: "stable"
---

# GLM-5.3-Flash NVFP4 with vLLM on 2× DGX Spark (128k context, with MTP)

GLM-5.3-Flash NVFP4 with vLLM on 2× DGX Spark (128k context, with MTP): 23 tok/s according to github.com (dataset as of Sep 29, 2026).

- Creator: [Weschera](https://www.contextstudios.ai/local-ai/creators/weschera.md)
- Engine: vLLM
- Quantization: NVFP4 (vcruz305-Quant, BF16-MTP-Head, 49 Shards; quantization_config.ignore für Layer 45), KV fp8_e4m3
- Model family: GLM-5.3-Flash
- Hardware: dgx-spark x2
- Context: 131072

## All numbers

- 23 tok/s (Everyday; Everyday, 1 request, prose prompt, with MTP4) — [source](https://github.com/Weschera/glm53-flash-2spark-tp2/blob/main/README.md)
- decode_tps: 23 (1 request) — [source](https://github.com/Weschera/glm53-flash-2spark-tp2/blob/main/README.md)
- decode_tps: 36.5 (1 request) — [source](https://github.com/Weschera/glm53-flash-2spark-tp2/blob/main/README.md)

## Weights

- [vcruz305/GLM-5.3-Flash-NVFP4](https://huggingface.co/vcruz305/GLM-5.3-Flash-NVFP4) (main, mit)

[https://github.com/Weschera/glm53-flash-2spark-tp2](https://github.com/Weschera/glm53-flash-2spark-tp2)

## Related

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