---
title: kindlingai/glm-5.3-flash-exlr8-k2-k3-k4
url: https://recentmodel.com/models/kindlingai/glm-5.3-flash-exlr8-k2-k3-k4/
status: just landed
published: 2026-10-14T13:59:14Z
updated: 2026-10-22T23:27:46Z
source: https://huggingface.co/kindlingai/glm-5.3-flash-exlr8-k2-k3-k4
---

# kindlingai/glm-5.3-flash-exlr8-k2-k3-k4

GLM-5.3-Flash is a MoE model: 45 layers (0-2 dense, 3-44 MoE), 288 routed experts with top-8 routing plus one shared expert per MoE layer, an MTP layer 45 and a vision tower. Mixture-of-experts (288 experts, 8 per token). Context: 1M tokens (config). License: mit. Vendor-reported: "GLM-5.3-Flash is a MoE model: 45 layers (0-2 dense, 3-44 MoE), 288 routed experts with top-8 routing plus one shared expert per MoE layer, an MTP layer 45 and a vision tower."

- Vendor-reported: GLM-5.3-Flash is a MoE model: 45 layers (0-2 dense, 3-44 MoE), 288 routed experts with top-8 routing plus one shared expert per MoE layer, an MTP layer 45 and a vision tower.

- **Org:** kindlingai
- **Released:** 2026-10-14
- **Status:** just landed
- **License:** mit (permissive)
- **Architecture:** MoE · 288 experts, 8/token · Glm5NextForConditionalGeneration
- **Context:** 1,048,576 tokens
- **Task:** image-text-to-text · vision
- **Signal:** 3 HF likes · 356502 downloads

## Links

- [Hugging Face](https://huggingface.co/kindlingai/glm-5.3-flash-exlr8-k2-k3-k4)
- [Ollama](https://ollama.com/library/glm-5.3-flash)