Skip to content

GLM 4.5 Air on M3 Ultra 256 GB: VRAM, speed and fit

GLM 4.5 Air at 8-bit runs on the M3 Ultra 256 GB with 128K of context at about 28 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on M3 Ultra 256 GB · 8-bit (Q8_0) · Ollama / LM Studio · Chat

GPU memory
197 GB
of 256 GB
Context
128K
auto
Speed
28 tok/s
12 when full
First reply
9.0 s
2K prompt

Where the memory goes

Model
109 GB
Context
23.0 GB
Overhead
680 MB
OS
64.0 GB
Free
59.0 GB
Memory
197 GB of 256 GB
Context
128K tokens · auto
Speed
28 tok/s · 12 when full
First reply
9.0 s for a 2K prompt
Running cost
$3.55/mo at home · $287/mo on a cloud 4× A40

Validation: Not validated

What GLM 4.5 Air on M3 Ultra 256 GB was checked against
CheckTargetResultStatus
Fits in GPU memory192 GB usable133 GB neededPass
Headroom5% free59.0 GB free (31%)Pass
Context for chat16K or more128KPass
Writing speed15 tok/s or more28 tok/sPass
First replyunder 3 s, 2K prompt9.0 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 Air
Parameters
110B, 15B active
Precision
8-bit (Q8_0)
Context
128K, auto
Chats at once
1
Use
Chat
Runs in
Ollama / LM Studio
Hardware
M3 Ultra 256 GB
GPU can use
192 GB of 256 GB

Running cost

At home
$3.55/mo
162 W at the wall
Renting instead
$287/mo
4× A40 at $2.36/h

4 h a day, power at $0.18 per kWh, cloud at RunPod on-demand prices as of Nov 22, 2026.

How to run it

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

GLM 4.5 Air on similar machines

All machines: GLM 4.5 Air VRAM requirements. Everything that runs here: what can the M3 Ultra 256 GB run?

Other models that run on M3 Ultra 256 GB

Questions

Can GLM 4.5 Air run on M3 Ultra 256 GB?

GLM 4.5 Air at 8-bit runs on the M3 Ultra 256 GB with 128K of context at about 28 tokens a second.

Report VR-06LRBU0, calculated Nov 22, 2026 from published specs, not benchmarked.