---
type: "Article"
title: "GLM-5.3-Flash 320B NVFP4 with vLLM on 2× DGX Spark (vision)"
description: "GLM-5.3-Flash 320B NVFP4 with vLLM on 2× DGX Spark (vision): recipe by sfxnz with speed, condition and source for every number, weights and license."
resource: "https://www.contextstudios.ai/local-ai/sfxnz--glm53-flash-nvfp4-dflash2-2x-dgx-spark"
language: "en"
generated:
  by: "process:contextstudios-md/1"
  at: "2026-10-02T20:34:14.895Z"
status: "stable"
---

# GLM-5.3-Flash 320B NVFP4 with vLLM on 2× DGX Spark (vision)

GLM-5.3-Flash 320B NVFP4 with vLLM on 2× DGX Spark (vision): 21.2 tok/s according to github.com (dataset as of Sep 29, 2026).

- Creator: [sfxnz](https://www.contextstudios.ai/local-ai/creators/sfxnz.md)
- Engine: vLLM
- Quantization: NVFP4 weight-only auf routed experts (~181 GiB), fp8_e4m3 KV (4.14-GiB-Pin), Marlin MoE, DFlash2-7
- Model family: GLM-5.3-Flash
- Hardware: dgx-spark x2
- Context: 327680
- Artificial Analysis Intelligence Index: 41.8 ([source](https://artificialanalysis.ai/models/glm-5-3-flash))

## All numbers

- 21.2 tok/s (Everyday; Everyday, 1 request, prose prompt, with DFlash2 (per recipe)) — [source](https://github.com/sfxnz/GLM-5.3-Flash-NVFP4-vLLM-2x-DGX-Spark/blob/main/README.md)
- decode_tps: 21.2 (1 request) — [source](https://github.com/sfxnz/GLM-5.3-Flash-NVFP4-vLLM-2x-DGX-Spark/blob/main/README.md)
- decode_tps: 67.64298009643134 (1 request) — [source](https://github.com/sfxnz/GLM-5.3-Flash-NVFP4-vLLM-2x-DGX-Spark/blob/main/evidence/rebench-20260902T204243Z/bench.txt)
- prefill_tps: 1425 (1 request) — [source](https://github.com/sfxnz/GLM-5.3-Flash-NVFP4-vLLM-2x-DGX-Spark/blob/main/README.md)

## Weights

- [LibertAIDAI/GLM-5.3-Flash-NVFP4](https://huggingface.co/LibertAIDAI/GLM-5.3-Flash-NVFP4) (main, mit)
- [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/sfxnz/GLM-5.3-Flash-NVFP4-vLLM-2x-DGX-Spark](https://github.com/sfxnz/GLM-5.3-Flash-NVFP4-vLLM-2x-DGX-Spark)

## Related

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