Measured model

Measured on a Mac Studio (M5 Max, 36GB)glm-4.7-flash:latest

Z.ai

On a Mac Studio (M5 Max, 36GB), glm-4.7-flash:latest answers a simple question in about 7.5 s, gets 76% of the Japanese knowledge questions right, 95% of the math problems, and uses 19.4GB of memory.

Results

MeasureResultAmong measured modelsNote
Reply timeabout 7.5 s24 of 33Until one simple common-sense question is answered (median of 50)
Knowledge (high school to university)76%19 of 33200 questions, ±6, 1 cut off (counted wrong)
Math (word problems)95%13 of 33100 questions, ±6
Memory used19.4GB28 of 33
EN→JA translation32 pts12 of 30out of 100 (chrF), about 23.3 s a sentence
JA→EN translation53 pts22 of 30out of 100 (chrF), about 19.9 s a sentence

"Among measured models" is the place among the 33 models measured on this site (lower is better for time and memory).

Measured on other Macs

The numbers and places on this page come from the Mac above alone.

Try it on your Mac

  1. Install the Mac version of Ollama from ollama.com and start it.
  2. Type this in Terminal. The first time, the model downloads; then you can chat with it.ollama run glm-4.7-flash:latest

It used 19.4GB here. To use it comfortably alongside other apps, a Mac with 48GB of memory or more is a good guide (the model then takes about half the memory).

About the model

Maker
Z.ai
Size
29.9B parameters
Quantization
Q4_K_M
Thinks before answering
Yes
Longest input at once
202,752 tokens
Released (Hugging Face)
Jan 19, 2026
Generation speed
81 tok/s
Start-up (loading)
about 5.9 s
Measured on
Nov 2, 2026
Ollama
0.34.3
Hugging Face
zai-org/GLM-4.7-Flash
Series
GLM

What the parts of a name mean (size, quantization and so on): how to read a model name.

Models of similar memory

Compare the main models on the text page. The series page lists every model measured.

Task recommendations and capabilities · Measurements by model