---
title: ukisai/Swift1.5-GLM-5.3-Flash
url: https://recentmodel.com/models/ukisai/Swift1.5-GLM-5.3-Flash/
status: just landed · new, unvetted
published: 2026-10-08T08:17:23Z
updated: 2026-10-30T11:19:53Z
source: https://huggingface.co/ukisai/Swift1.5-GLM-5.3-Flash
---

# ukisai/Swift1.5-GLM-5.3-Flash

Swift 1.5 GLM-5.3-Flash is a derivative of GLM-5.3-Flash (Copyright (c) 2026 Z.AI Co., Ltd, MIT License). Mixture-of-experts, 321B total (288 experts, 8 per token). Context: 1M tokens (config). License: swift-open-license-1.0.


- **Org:** ukisai
- **Released:** 2026-10-08
- **Status:** just landed · new, unvetted
- **License:** swift-open-license-1.0 (restricted)
- **Parameters:** 321.3B
- **Architecture:** MoE · 288 experts, 8/token · Glm5NextForConditionalGeneration
- **Context:** 1,048,576 tokens
- **Task:** image-text-to-text · vision
- **Signal:** 2 HF likes · 43 downloads

## Runs on

real quant files; sizing calculation, not tested.

- Q4 ~202.2 GB: 2× DGX Spark (256GB), CPU only, 256GB RAM (slow)
- Q8 ~342.9 GB: Mac 512GB
- FP16 ~643.1 GB: no listed device

## Links

- [Hugging Face](https://huggingface.co/ukisai/Swift1.5-GLM-5.3-Flash)
- [Ollama](https://ollama.com/library/glm-5.3-flash)
- [GGUF: ukisai/Swift-1.5-GLM-5.3-Flash-GGUF](https://huggingface.co/ukisai/Swift-1.5-GLM-5.3-Flash-GGUF)
- [quant: ukisai/Swift-1.5-GLM-5.3-Flash-NVFP4](https://huggingface.co/ukisai/Swift-1.5-GLM-5.3-Flash-NVFP4)
- [quant: ukisai/Swift-1.5-GLM-5.3-Flash-W4A16-AWQ](https://huggingface.co/ukisai/Swift-1.5-GLM-5.3-Flash-W4A16-AWQ)