---
type: "Article"
title: "GLM-5.2 753B NVFP4 with vLLM on 3× DGX Spark"
description: "GLM-5.2 753B NVFP4 with vLLM on 3× DGX Spark: recipe by MiaAI-Lab with speed, condition and source for every number, weights and license."
resource: "https://www.contextstudios.ai/local-ai/miaai-lab--glm-5.2-nvfp4-aqlm-triple-dgx-sparks"
language: "en"
generated:
  by: "process:contextstudios-md/1"
  at: "2026-10-02T18:23:28.246Z"
status: "stable"
---

# GLM-5.2 753B NVFP4 with vLLM on 3× DGX Spark

GLM-5.2 753B NVFP4 with vLLM on 3× DGX Spark: 13.6 tok/s according to github.com (dataset as of Sep 29, 2026).

- Creator: [MiaAI-Lab](https://www.contextstudios.ai/local-ai/creators/miaai-lab.md)
- Engine: vLLM custom :k12l1-vision
- Quantization: NVFP4+AQLM hybrid, nvfp4_ds_mla KV
- Model family: GLM-5.2
- Hardware: dgx-spark x3
- Context: 380928

## All numbers

- 13.6 tok/s (Mixed; Mixed, 1 request, mixed prompt set, with MTP (per recipe)) — [source](https://github.com/MiaAI-Lab/GLM-5.2-NVFP4-AQLM-Triple-DGX-Sparks/blob/main/README.md#L91)
- decode_tps: 13.6 (1 request) — [source](https://github.com/MiaAI-Lab/GLM-5.2-NVFP4-AQLM-Triple-DGX-Sparks/blob/main/README.md#L91)
- decode_tps: 20.9 (1 request) — [source](https://github.com/MiaAI-Lab/GLM-5.2-NVFP4-AQLM-Triple-DGX-Sparks/blob/main/README.md#L91)

## Weights

- [jarrelscy/GLM-5.2-NVFP4-AQLM-hybrid](https://huggingface.co/jarrelscy/GLM-5.2-NVFP4-AQLM-hybrid) (main, mit)
- [sapidlabs/Sparkulator-GLM-5.2](https://huggingface.co/sapidlabs/Sparkulator-GLM-5.2) (draft, mit)
- [RedHatAI/GLM-5.2-speculator.dspark-preview](https://huggingface.co/RedHatAI/GLM-5.2-speculator.dspark-preview) (draft, mit)

[https://github.com/MiaAI-Lab/GLM-5.2-NVFP4-AQLM-Triple-DGX-Sparks](https://github.com/MiaAI-Lab/GLM-5.2-NVFP4-AQLM-Triple-DGX-Sparks)

## Related

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