Can I Run GLM-6 on Mac Studio (M3 Ultra, 256 GB)?

Written by Jakub Rusinowski · Last updated June 26, 2026

Yes — comfortably

Yes, comfortably — GLM-6 9B at Q8_0 needs about 11.6 GB of the 192 GB usable on Mac Studio (M3 Ultra, 256 GB), leaving ~180.4 GB spare and running at ~39 tok/s (estimated), with room for about 65,536 tokens of context.

Confidence: medium · Recommended quantization: Q8_0 · Estimated speed: ~39 tok/s

Mac Studio (M3 Ultra, 256 GB) — what it gives a model

Usable memory for models192 GB
Memory bandwidth819 GB/s
Form factorDesktop
Operating systemmacOS
Memory upgradeableNo — soldered

GLM-6 on Mac Studio (M3 Ultra, 256 GB): memory by quantization

QuantMemory neededFits 192 GB?Max contextEst. speedDownload
F1620 GB✓ Yes64K~22.5 tok/s18 GB
Q8_011.6 GB✓ Yes64K~39 tok/s9.6 GB
Q6_K9.4 GB✓ Yes64K~48.1 tok/s7.4 GB
Q5_K_M8.4 GB✓ Yes64K~53.9 tok/s6.4 GB
Q4_K_M7.4 GB✓ Yes64K~60.8 tok/s5.4 GB
Q3_K_M5.8 GB✓ Yes64K~77.6 tok/s3.8 GB
Q2_K5 GB✓ Yes64K~91.4 tok/s3 GB

Which GLM-6 sizes fit

VariantNeeds at Q4_K_MFits?Est. speed
GLM-6 355B-A32B219.2 GB✗ Too large
GLM-6 9B7.4 GB✓ Fits~60.8 tok/s

What to watch out for

Mac Studio M3 Ultra 256 GB limitations

Recommended setup

Ollama or LM Studio (Metal) — MLX for the fastest Apple-native throughput

How these numbers are calculated

FAQ

Can I run GLM-6 on Mac Studio (M3 Ultra, 256 GB)?

Yes, comfortably — GLM-6 9B at Q8_0 needs about 11.6 GB of the 192 GB usable on Mac Studio (M3 Ultra, 256 GB), leaving ~180.4 GB spare and running at ~39 tok/s (estimated), with room for about 65,536 tokens of context.

Which quantization of GLM-6 should I use on Mac Studio (M3 Ultra, 256 GB)?

Q8_0 — it needs about 11.6 GB of the 192 GB available, downloads as roughly 9.6 GB, and runs at an estimated 39 tokens/sec with up to 64K of context.

What limits GLM-6 on Mac Studio (M3 Ultra, 256 GB)?

Nothing binding — the model fits with headroom and generates at a usable speed on this hardware.

Which runtime should I use?

Ollama or LM Studio (Metal) — MLX for the fastest Apple-native throughput

Other Computers

Other Models on Mac Studio (M3 Ultra, 256 GB)

GLM-6 on GPUs

What This Model Is Good At

Model & Tools

← Can I Run It? | GLM-6 model page | Check your hardware