Skip to content

GLM 4.5 Air on DGX Station GB300: VRAM, speed and fit

GLM 4.5 Air at 8-bit runs on the DGX Station GB300 with 128K of context at about 168 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on DGX Station GB300 · 8-bit (Q8_0) · Ollama / LM Studio · Chat

GPU memory
133 GB
of 252 GB
Context
128K
auto
Speed
168 tok/s
92 when full
First reply
0.3 s
2K prompt

Where the memory goes

Model
109 GB
Context
23.0 GB
Overhead
885 MB
OS
0.0 GB
Free
119 GB
In RAM
0.0 GB
Memory
133 GB of 252 GB
Context
128K tokens · auto
Speed
168 tok/s · 92 when full
First reply
0.3 s for a 2K prompt
Running cost
$23/mo at home · $287/mo on a cloud 4× A40

Validation: Validated

What GLM 4.5 Air on DGX Station GB300 was checked against
CheckTargetResultStatus
Fits in GPU memory252 GB usable133 GB neededPass
Headroom5% free119 GB free (47%)Pass
Context for chat16K or more128KPass
Writing speed15 tok/s or more168 tok/sPass
First replyunder 3 s, 2K prompt0.3 sPass

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
DGX Station GB300
GPU can use
252 GB of 252 GB
Spill space
480 GB LPDDR5X on the Grace CPU

Running cost

At home
$23/mo
1040 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 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 DGX Station GB300 run?

Other models that run on DGX Station GB300

Questions

Can GLM 4.5 Air run on DGX Station GB300?

GLM 4.5 Air at 8-bit runs on the DGX Station GB300 with 128K of context at about 168 tokens a second.

Report VR-0BYOTXK, calculated Nov 22, 2026 from published specs, not benchmarked.