---
type: "Article"
title: "GLM-5.3-Flash 320B-A18B Q4_K with mlx-serve (ds4) on 1× Mac (M5 Ultra)"
description: "GLM-5.3-Flash 320B-A18B Q4_K with mlx-serve (ds4) on 1× Mac (M5 Ultra): recipe by drowzeys with speed, condition and source for every number, weights and license."
resource: "https://www.contextstudios.ai/local-ai/drowzeys--mac-glm53-flash-q4k-ds4-mlx-serve"
language: "en"
generated:
  by: "process:contextstudios-md/1"
  at: "2026-10-24T16:13:50.721Z"
status: "stable"
---

# GLM-5.3-Flash 320B-A18B Q4_K with mlx-serve (ds4) on 1× Mac (M5 Ultra)

GLM-5.3-Flash 320B-A18B Q4_K with mlx-serve (ds4) on 1× Mac (M5 Ultra): 35.8 tok/s according to github.com (dataset as of Sep 29, 2026).

- Creator: [drowzeys](https://www.contextstudios.ai/local-ai/creators/drowzeys.md)
- Engine: mlx-serve 26.9.7-dev @933566c + ds4 9139e2a (GGUF-Backend)
- Quantization: GGUF Q4_K (antirez, 177.8 GiB), kompakter DSA-KV
- Model family: GLM-5.3-Flash
- Hardware: mac x1
- Context: 262144
- Artificial Analysis Intelligence Index: 41.8 ([source](https://artificialanalysis.ai/models/glm-5-3-flash))

## All numbers

- 35.8 tok/s (Everyday; Everyday, 1 request, llmprobe standard prompt, thinking on, with embedded MTP (2 draft tokens) (per recipe)) — [source](https://github.com/drowzeys/keys-Independent-Bench-MLX-Serve-26.9.7-dev-GLM-5.3-Flash-Q4_K-GGUF-ds4#headline)
- decode_tps: 35.8 (1 request) — [source](https://github.com/drowzeys/keys-Independent-Bench-MLX-Serve-26.9.7-dev-GLM-5.3-Flash-Q4_K-GGUF-ds4#headline)
- decode_tps: 41 (1 request) — [source](https://github.com/drowzeys/keys-Independent-Bench-MLX-Serve-26.9.7-dev-GLM-5.3-Flash-Q4_K-GGUF-ds4#headline)
- prefill_tps: 438.8 (1 request) — [source](https://github.com/drowzeys/keys-Independent-Bench-MLX-Serve-26.9.7-dev-GLM-5.3-Flash-Q4_K-GGUF-ds4#headline)
- ttft_ms: 427 (1 request) — [source](https://github.com/drowzeys/keys-Independent-Bench-MLX-Serve-26.9.7-dev-GLM-5.3-Flash-Q4_K-GGUF-ds4#headline)

## Weights

- [antirez/glm-5.3-flash-gguf](https://huggingface.co/antirez/glm-5.3-flash-gguf) (main)
- [zai-org/GLM-5.3-Flash](https://huggingface.co/zai-org/GLM-5.3-Flash) (base, mit)

[https://github.com/drowzeys/keys-Independent-Bench-MLX-Serve-26.9.7-dev-GLM-5.3-Flash-Q4_K-GGUF-ds4](https://github.com/drowzeys/keys-Independent-Bench-MLX-Serve-26.9.7-dev-GLM-5.3-Flash-Q4_K-GGUF-ds4)

## Related

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