# Z.ai

## Models

- [glm-5-3](/qc69jvmznzxy/glm-5-3.md) — 753B-parameter text MoE with DeepSeek-style sparse attention, native FP8 weights, reasoning and tool calling.
- [glm-5-3-flash](/qc69jvmznzxy/glm-5-3-flash.md) — Multimodal 320B-total / 18B-active MoE with hybrid KDA and sparse MLA attention, native FP8 weights, reasoning and tool calling.
- [glm-5-3](/qc69jvmznzxy/glm-5-3.md) — 753B-parameter text MoE with DeepSeek-style sparse attention, native FP8 weights, reasoning and tool calling.
- [glm-5-3-flash](/qc69jvmznzxy/glm-5-3-flash.md) — Multimodal 320B-total / 18B-active MoE with hybrid KDA and sparse MLA attention, native FP8 weights, reasoning and tool calling.