Skip to content

GLM 4.5 Air on Dual DGX Spark: VRAM, speed and fit

GLM 4.5 Air at 8-bit runs on the DGX Spark 128 GB with 128K of context at about 12 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on DGX Spark 128 GB · 8-bit (Q8_0) · Ollama / LM Studio · Chat

GPU memory
149 GB
of 256 GB
Context
128K
auto
Speed
12 tok/s
4.6 when full
First reply
1.9 s
2K prompt

Where the memory goes

Model
109 GB
Context
23.0 GB
Overhead
1.1 GB
OS
15.4 GB
Free
107 GB
Memory
149 GB of 256 GB
Context
128K tokens · auto
Speed
12 tok/s · 4.6 when full
First reply
1.9 s for a 2K prompt
Running cost
$3.15/mo at home · $287/mo on a cloud 4× A40

Validation: Validated with conditions

What GLM 4.5 Air on Dual DGX Spark was checked against
CheckTargetResultStatus
Fits in GPU memory241 GB usable133 GB neededPass
Headroom5% free107 GB free (45%)Pass
Context for chat16K or more128KPass
Writing speed15 tok/s or more12 tok/sCheck
First replyunder 3 s, 2K prompt1.9 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 Spark 128 GB
GPU can use
241 GB of 256 GB

Running cost

At home
$3.15/mo
144 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 Dual DGX Spark run?

Other models that run on Dual DGX Spark

Questions

Can GLM 4.5 Air run on Dual DGX Spark?

GLM 4.5 Air at 8-bit runs on the DGX Spark 128 GB with 128K of context at about 12 tokens a second.

Report VR-031GRDD, calculated Nov 22, 2026 from published specs, not benchmarked.