---
type: "Article"
title: "GLM-5.2 753B INT4/INT8 with vLLM on 4× DGX Spark"
description: "GLM-5.2 753B INT4/INT8 with vLLM on 4× DGX Spark: recipe by Weschera with speed, condition and source for every number, weights and license."
resource: "https://www.contextstudios.ai/local-ai/weschera--glm52-quanttrio-int4-int8-mtp5-4x-dgx-spark"
language: "en"
generated:
  by: "process:contextstudios-md/1"
  at: "2026-10-02T21:56:36.799Z"
status: "stable"
---

# GLM-5.2 753B INT4/INT8 with vLLM on 4× DGX Spark

GLM-5.2 753B INT4/INT8 with vLLM on 4× DGX Spark: 32.5 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: QuantTrio Int4-Int8Mix (W4A16 MoE-Experts / W8A16 dense+MTP, compressed-tensors, data-free; Layer 0 + Attention-Indexer BF16); KV nvfp4_ds_mla (400 B/Token)
- Model family: GLM-5.2
- Hardware: dgx-spark x4
- Context: 316000

## All numbers

- 32.5 tok/s (Peak; Peak, 1 request, best value reported by source, context 200k) — [source](https://github.com/Weschera/GLM-5.2-QuantTrio-4x-DGX-Spark/blob/main/README.md)
- decode_tps: 32.5 (1 request) — [source](https://github.com/Weschera/GLM-5.2-QuantTrio-4x-DGX-Spark/blob/main/README.md)

## Weights

- [QuantTrio/GLM-5.2-Int4-Int8Mix](https://huggingface.co/QuantTrio/GLM-5.2-Int4-Int8Mix) (main, mit)

[https://github.com/Weschera/GLM-5.2-QuantTrio-4x-DGX-Spark](https://github.com/Weschera/GLM-5.2-QuantTrio-4x-DGX-Spark)

## Related

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