Memory at each precision
| Version | Weights | With context | Smallest Mac |
|---|---|---|---|
| 8-bit | 340 GB | 367 GB | 512 GB |
| 6-bit | 260 GB | 281 GB | 512 GB |
| 4-bit | 180 GB | 194 GB | 512 GB |
| 3-bit lower quality | 140 GB | 151 GB | 256 GB |
| 2-bit lower quality | 100 GB | 108 GB | 192 GB |
On every Apple chip
The smallest memory size of each chip that runs GLM-5.3 Flash, the best version that fits it, and the writing speed you can expect.
| Chip | Needs | Version | Tokens/s |
|---|---|---|---|
| M6 | no size fits | Too big | – |
| M5 Ultra | 512 GB | 8-bit Runs well | 28–50 |
| M5 Max | 128 GB | 2-bit Only just | 49–88 |
| M5 Pro | no size fits | Too big | – |
| M5 | no size fits | Too big | – |
| M4 Max | 128 GB | 2-bit Only just | 44–78 |
| M4 Pro | no size fits | Too big | – |
| M4 | no size fits | Too big | – |
| M3 Ultra | 512 GB | 8-bit Runs well | 19–34 |
| M3 Max | 128 GB | 2-bit Only just | 32–57 |
| M3 Pro | no size fits | Too big | – |
| M3 | no size fits | Too big | – |
| M2 Ultra | 192 GB | 2-bit Runs well | 64–114 |
| M2 Max | no size fits | Too big | – |
| M2 Pro | no size fits | Too big | – |
| M2 | no size fits | Too big | – |
| M1 Ultra | 128 GB | 2-bit Only just | 64–114 |
| M1 Max | no size fits | Too big | – |
| M1 Pro | no size fits | Too big | – |
| M1 | no size fits | Too big | – |
How to run it
- The easy way: download MLX Harness, free and open source. Search for GLM-5.3 Flash, download the version that fits your Mac, and chat. It also serves the model to your other apps over an OpenAI-compatible API.Download MLX HarnessFree · Apple Silicon · macOS 14.5 or later
- In Terminal with Apple’s MLX:
pip install mlx-lmmlx_lm.chat --model mlx-community/GLM-5.3-Flash-4bitBuild: mlx-community/GLM-5.3-Flash-4bit on Hugging Face. Other precisions sit next to it.
Step by step: download and run LLMs on a Mac · how to use MLX Harness · MLX vs Ollama vs llama.cpp
About GLM-5.3 Flash
| Made by | Z.ai (Zhipu) |
|---|---|
| Parameters | 320B total · 18B active (mixture of experts) |
| Context | 1M tokens |
| Licence | MIT |
| Released | 2026-08 |
| Input | Text and images |
| Intelligence | 41.8 on the Artificial Analysis Intelligence Index |
| Weights | zai-org/GLM-5.3-Flash |
Questions
- How much memory does GLM-5.3 Flash need?
- About 180 GB of weights at 4-bit, plus room for the context: 194 GB in all. On a Mac that means 512 GB of unified memory or more, since macOS lets the GPU use about 75% of it by default.
- How fast is GLM-5.3 Flash on a Mac?
- Writing speed depends on memory bandwidth. The fastest Mac for it here is an M5 Ultra with 512 GB at about 28–50 tokens a second (8-bit). The smallest Mac that runs it, with 512 GB, manages about 28–50 on an M5 Ultra.
- Why does GLM-5.3 Flash run faster than its size suggests?
- It is a mixture-of-experts model: it holds 320B parameters in memory but reads only 18B for each token, so it writes at the speed of a much smaller model.
Similar models
For your model card or README
Shows the smallest Mac that runs GLM-5.3 Flash well and links here.
[](https://mlx.app/run/glm-5.3-flash)How it’s worked out
Memory: the model’s parameters at 8, 6, 4, 3 or 2 bits per weight plus MLX’s group scales (half a bit per weight), or its native format, with room for the context on top. By default macOS lets the GPU use about 75% of unified memory. Speed: memory bandwidth divided by the bytes read per token is the ceiling for one conversation; in llama.cpp’s public Apple Silicon benchmarks real runs reach about 45% to 80% of it, which is the range shown. These are estimates, not measurements: measure your own Mac on MLX Bench. Model figures from each official model card, chip figures from Apple’s Tech Specs. Checked 2026-10-19. Same data as mlx.app/compare.