---
type: "Article"
title: "GLM-5.2 753.3B EXL3 3.5 bpw with vLLM on 4× DGX Spark"
description: "GLM-5.2 753.3B EXL3 3.5 bpw with vLLM on 4× DGX Spark: recipe by fujitsupolycom with speed, condition and source for every number, weights and license."
resource: "https://www.contextstudios.ai/local-ai/fujitsupolycom--glm-5.2-exl3-3.5bpw-tp4-4x-dgx-spark"
language: "en"
generated:
  by: "process:contextstudios-md/1"
  at: "2026-10-02T20:34:54.229Z"
status: "stable"
---

# GLM-5.2 753.3B EXL3 3.5 bpw with vLLM on 4× DGX Spark

GLM-5.2 753.3B EXL3 3.5 bpw with vLLM on 4× DGX Spark: 20.2 tok/s according to github.com (dataset as of Sep 29, 2026).

- Creator: [fujitsupolycom](https://www.contextstudios.ai/local-ai/creators/fujitsupolycom.md)
- Engine: vLLM
- Quantization: EXL3 3.5 bpw gemischt (TR3v4), dynamisches NVFP4 MLA + FP8 RoPE KV (nvfp4_ds_mla), target-only exact Q40
- Model family: GLM-5.2
- Hardware: dgx-spark x4
- Context: 1048576
- Artificial Analysis Intelligence Index: 33.7 ([source](https://artificialanalysis.ai/models/glm-5-2))

## All numbers

- 20.2 tok/s (Everyday; Everyday, 1 request, realistic prompt, with MTP (fixed-4, greedy Draft) (per recipe)) — [source](https://github.com/FujitsuPolycom/sparkring/blob/main/performance/records/glm-3.5bpw/normalized-base-20260822.md)
- decode_tps: 20.15 (1 request) — [source](https://github.com/FujitsuPolycom/sparkring/blob/main/performance/records/glm-3.5bpw/normalized-base-20260822.md)
- decode_tps: 25.39 (1 request) — [source](https://github.com/FujitsuPolycom/sparkring/blob/main/performance/records/glm-3.5bpw/normalized-base-20260822.md)
- prefill_tps: 671 (1 request) — [source](https://github.com/FujitsuPolycom/sparkring/blob/main/performance/records/glm-3.5bpw/normalized-base-20260822.md)

## Weights

- [brandonmusic/GLM-5.2-EXL3-TR3v4-3.5bpw-MTP78](https://huggingface.co/brandonmusic/GLM-5.2-EXL3-TR3v4-3.5bpw-MTP78) (main, mit)

[https://github.com/FujitsuPolycom/sparkring](https://github.com/FujitsuPolycom/sparkring)

## Related

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