Skip to content

GLM 4.5 Air on M5 Max 128 GB: VRAM, speed and fit

GLM 4.5 Air at 6-bit runs on the M5 Max 128 GB with 32K of context at about 30 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on M5 Max 128 GB · 6-bit (Q6_K) · Ollama / LM Studio · Chat

GPU memory
123 GB
of 128 GB
Context
32K
auto
Speed
30 tok/s
22 when full
First reply
4.7 s
2K prompt

Where the memory goes

Model
84.4 GB
Context
5.8 GB
Overhead
680 MB
OS
32.0 GB
Free
5.2 GB
Memory
123 GB of 128 GB
Context
32K tokens · auto
Speed
30 tok/s · 22 when full
First reply
4.7 s for a 2K prompt
Running cost
$2.63/mo at home · $131/mo on a cloud 4× RTX A5000

Validation: Validated with conditions

What GLM 4.5 Air on M5 Max 128 GB was checked against
CheckTargetResultStatus
Fits in GPU memory96.0 GB usable90.8 GB neededPass
Headroom5% free5.2 GB free (5%)Pass
Context for chat16K or more32KPass
Writing speed15 tok/s or more30 tok/sPass
First replyunder 3 s, 2K prompt4.7 sCheck

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
6-bit (Q6_K)
Context
32K, auto
Chats at once
1
Use
Chat
Runs in
Ollama / LM Studio
Hardware
M5 Max 128 GB
GPU can use
96.0 GB of 128 GB

Worth trying

  • 8-bit cache: Room for 64K context

Running cost

At home
$2.63/mo
120 W at the wall
Renting instead
$131/mo
4× RTX A5000 at $1.08/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-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 M5 Max 128 GB run?

Other models that run on M5 Max 128 GB

Questions

Can GLM 4.5 Air run on M5 Max 128 GB?

GLM 4.5 Air at 6-bit runs on the M5 Max 128 GB with 32K of context at about 30 tokens a second.

Report VR-1O4C21G, calculated Nov 22, 2026 from published specs, not benchmarked.