---
type: "Article"
title: "GLM-5.3-Flash 320B EXL3 4 bpw with vLLM on 3× DGX Spark"
description: "GLM-5.3-Flash 320B EXL3 4 bpw 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-5.3-flash-exl3-2x-dgx-sparks-3x"
language: "en"
generated:
  by: "process:contextstudios-md/1"
  at: "2026-10-01T20:41:09.765Z"
status: "stable"
---

# GLM-5.3-Flash 320B EXL3 4 bpw with vLLM on 3× DGX Spark

GLM-5.3-Flash 320B EXL3 4 bpw with vLLM on 3× DGX Spark: 39.6 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
- Quantization: EXL3/TR3 4 bpw (routed experts), FP8 KV (fp8_ds_mla)
- Model family: GLM-5.3-Flash
- Hardware: dgx-spark x3
- Context: 1000000
- Artificial Analysis Intelligence Index: 41.8 ([source](https://artificialanalysis.ai/models/glm-5-3-flash))

## All numbers

- 39.6 tok/s (Everyday; Everyday, 1 request, prose prompt, with DFlash2 (per recipe)) — [source](https://github.com/MiaAI-Lab/GLM-5.3-Flash-EXL3-2x-DGX-Sparks/blob/main/README.md#L1272)
- decode_tps: 39.6 (1 request) — [source](https://github.com/MiaAI-Lab/GLM-5.3-Flash-EXL3-2x-DGX-Sparks/blob/main/README.md#L1272)
- decode_tps: 87.8 (1 request) — [source](https://github.com/MiaAI-Lab/GLM-5.3-Flash-EXL3-2x-DGX-Sparks/blob/main/README.md#L1272)

## Weights

- [Mia-AiLab/GLM-5.3-Flash-EXL3-TR3-4bpw](https://huggingface.co/Mia-AiLab/GLM-5.3-Flash-EXL3-TR3-4bpw) (main, other)
- [incoai/GLM-5.3-Flash-DFlash2](https://huggingface.co/incoai/GLM-5.3-Flash-DFlash2) (draft, cc-by-nc-nd-4.0)

[https://github.com/MiaAI-Lab/GLM-5.3-Flash-EXL3-2x-DGX-Sparks](https://github.com/MiaAI-Lab/GLM-5.3-Flash-EXL3-2x-DGX-Sparks)

## Related

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