Skip to content
Local AI Wizard
Your machine
Theme

GLM-5.3 family: which size to run

2 sizes, 320B–744B parameters · Z.ai

Checked

Sizes

GLM-5.3 sizes
ModelArchitecture
GLM-5.3 FlashZ.ai · MIT · Aug 26, 2026320BMoE · 18B active1,048,57671.6248242No GGUF Q4_K_M file (plain or UD-) in the repository collected204
GLM-5.3Z.ai · GLM-5.3 · Aug 18, 2026744BMoE · 40B active1,048,57676.1566560No GGUF Q4_K_M file (plain or UD-) in the repository collected418.3

Each size is its own model, with its own scores and memory needs. Q4 estimates are planning figures, not measurements; file sizes are published. The Mac or PC column is for a 32 GB or larger machine (8 GB reserve); machines under 32 GB reserve 25% of their memory (2 to 8 GB), so they need less. The publisher lists GLM-5.3 744B-A40B, GLM-5.3-Flash 320B-A18B.

GLM-5.3 Flash starts from a newly trained base model, so it is not GLM-5.3 made smaller: the two sizes differ in base model as well as in parameters.

How to read this table

Q4 means compressed to about 4 bits per weight. GGUF (llama.cpp, Ollama, LM Studio) and MLX (Apple silicon) are file formats; the sizes shown are the published 4-bit files. A dash means no value is published or collected for that size; the reason is in the cell's accessible text.

Which size fits my machine

The largest size whose Q4 planning estimate fits what each machine offers. A planning estimate, not a measurement and not a speed. Smaller machines are left out; the largest one that fits no size is kept to show the limit.

Largest GLM-5.3 size per machine
MachineLargest GLM-5.3 size with enough memory
Mac Studio M5 Max · 128 GB unified104No size of this family has a Q4 estimate within what this machine offersNo size fits, so there is no estimate to compare
Mac Studio · M5 Ultra · 36-core CPU / 80-core GPU · 512 GB unified392GLM-5.3 Flash248
RTX 5090 · 32 GB VRAM32No size of this family has a Q4 estimate within what this machine offersNo size fits, so there is no estimate to compare
DGX H100 · 8 × 80 GB640GLM-5.3574

A dash means no size of this family fits that machine. The requirement is the size's Q4 estimate with that machine's own reserve: a graphics card reserves 2 GB, as in the sizes table; a Mac or PC reserves 25% of its memory (2 to 8 GB), so below 32 GB its figure is lower than the sizes table's. A server profile reserves 2 GB per graphics card, so its figure is higher.

Smallest machine for each size

The profile with the least memory that still has enough for the size's Q4 estimate, from the hardware catalog.

Smallest machine per GLM-5.3 size
SizeSmallest Mac or PC-memory profileSmallest graphics-card profileServer-class profile
GLM-5.3 FlashMac Studio 2026 · M5 Ultra · 512 GBNo graphics-card profile in the catalog has enough memory for this sizeDGX H100 · 8 × 80 GB · 640 GB
GLM-5.3No Mac, laptop or PC profile in the catalog has enough memory for this sizeNo graphics-card profile in the catalog has enough memory for this sizeDGX H100 · 8 × 80 GB · 640 GB

A dash means no profile of that kind in the catalog has enough memory for the size.

Memory by file precision

The same planning formula at three precisions (0.625, 1.125 and 2 bytes per parameter, plus working room and the system reserve). Estimates, not measurements.

GLM-5.3 memory estimate by precision
Size
GLM-5.3 Flash248242440434776770
GLM-5.35665601,0131,0071,7941,788

Family tree

Family, sizes and, for each size, the two 4-bit files the tables use (GGUF Q4_K_M and MLX 4-bit) when one was collected. Other precisions are not drawn here.

GLM-5.3 family: sizes and published filesSwipe sideways to see the files, or read the list below.
GLM-5.3 family: sizes and published filesFamilySizesFilesGLM-5.3Z.aiFlash 320B A18B18B activeMLX 4-bit204 GB744B A40B40B activeMLX 4-bit418.3 GB

The same tree as a list:

  • GLM-5.3 · Z.ai

Learn more

Sources

Where the family and its sizes are named, and where each number comes from.