Skip to content

GLM 4.5 on M5 Ultra 512 GB: VRAM, speed and fit

GLM 4.5 at 8-bit runs on the M5 Ultra 512 GB with 24K of context at about 16 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on M5 Ultra 512 GB · 8-bit (Q8_0) · Ollama / LM Studio · Chat

GPU memory
492 GB
of 512 GB
Context
24K
auto
Speed
16 tok/s
14 when full
First reply
7.0 s
2K prompt

Where the memory goes

Model
355 GB
Context
8.6 GB
Overhead
712 MB
OS
128 GB
Free
20.1 GB
Memory
492 GB of 512 GB
Context
24K tokens · auto
Speed
16 tok/s · 14 when full
First reply
7.0 s for a 2K prompt
Running cost
$5.06/mo at home · $574/mo on a cloud 8× A40

Validation: Not validated

What GLM 4.5 on M5 Ultra 512 GB was checked against
CheckTargetResultStatus
Fits in GPU memory384 GB usable364 GB neededPass
Headroom5% free20.1 GB free (5%)Pass
Context for chat16K or more24KPass
Writing speed15 tok/s or more16 tok/sPass
First replyunder 3 s, 2K prompt7.0 sFails

Targets: a reply you can read along with, a first reply the use case tolerates, and 5% of memory left free. Calculated from published specs, not benchmarked.

The setup

Model
GLM 4.5
Parameters
358B, 35.6B active
Precision
8-bit (Q8_0)
Context
24K, auto
Chats at once
1
Use
Chat
Runs in
Ollama / LM Studio
Hardware
M5 Ultra 512 GB
GPU can use
384 GB of 512 GB

Worth trying

  • 8-bit cache: Room for 48K context

Running cost

At home
$5.06/mo
231 W at the wall
Renting instead
$574/mo
8× A40 at $4.72/h

4 h a day, power at $0.18 per kWh, cloud at RunPod on-demand prices as of Nov 21, 2026.

How to run it

llama.cpp
llama-server -hf unsloth/GLM-4.5-GGUF
vLLM
vllm serve zai-org/GLM-4.5
MLX (Mac)
mlx_lm.chat --model mlx-community/GLM-4.5-4bit

GLM 4.5 on similar machines

  • M5 Max 128 GBToo big
  • M3 Ultra 96 GBToo big
  • M3 Ultra 256 GBRuns
  • M3 Ultra 512 GBRuns
  • Ryzen AI Max+ 395 64 GBToo big
  • Ryzen AI Max+ 395 128 GBToo big
  • RTX SparkJust misses
  • DGX SparkJust misses

All machines: GLM 4.5 VRAM requirements. Everything that runs here: what can the M5 Ultra 512 GB run?

Other models that run on M5 Ultra 512 GB

Questions

Can GLM 4.5 run on M5 Ultra 512 GB?

GLM 4.5 at 8-bit runs on the M5 Ultra 512 GB with 24K of context at about 16 tokens a second.

Report VR-1WG63FX, calculated Nov 22, 2026 from published specs, not benchmarked.