Skip to content

GLM-5.3 Flash on DGX Spark: VRAM, speed and fit

GLM-5.3 Flash at 2-bit runs on the DGX Spark 128 GB with 104K of context at about 26 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on DGX Spark 128 GB · 2-bit (Q2_K) · Ollama / LM Studio · Chat

GPU memory
122 GB
of 128 GB
Context
104K
auto
Speed
26 tok/s
22 when full
First reply
3.9 s
2K prompt

Where the memory goes

Model
112 GB
Context
1.4 GB
Overhead
687 MB
OS
7.7 GB
Free
6.0 GB
Memory
122 GB of 128 GB
Context
104K tokens · auto
Speed
26 tok/s · 22 when full
First reply
3.9 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-5.3 Flash on DGX Spark was checked against
CheckTargetResultStatus
Fits in GPU memory120 GB usable114 GB neededPass
Headroom5% free6.0 GB free (5%)Pass
Context for chat16K or more104KPass
Writing speed15 tok/s or more26 tok/sPass
First replyunder 3 s, 2K prompt3.9 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-5.3 Flash
Parameters
321B, 18B active
Precision
2-bit (Q2_K)
Context
104K, auto
Chats at once
1
Use
Chat
Runs in
Ollama / LM Studio
Hardware
DGX Spark 128 GB
GPU can use
120 GB of 128 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-5.3-Flash-GGUF
vLLM
vllm serve zai-org/GLM-5.3-Flash
MLX (Mac)
mlx_lm.chat --model mlx-community/GLM-5.3-Flash-4bit

GLM-5.3 Flash on similar machines

All machines: GLM-5.3 Flash VRAM requirements. Everything that runs here: what can the DGX Spark run?

Other models that run on DGX Spark

Questions

Can GLM-5.3 Flash run on DGX Spark?

GLM-5.3 Flash at 2-bit runs on the DGX Spark 128 GB with 104K of context at about 26 tokens a second.

Report VR-1OFQR5Z, calculated Nov 22, 2026 from published specs, not benchmarked.