Skip to content

Hy3 on Dual DGX Spark: VRAM, speed and fit

Hy3 at 5-bit runs on the DGX Spark 128 GB with 96K of context at about 12 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on DGX Spark 128 GB · 5-bit (Q5_K_M) · Ollama / LM Studio · Chat

GPU memory
242 GB
of 256 GB
Context
96K
auto
Speed
12 tok/s
4.0 when full
First reply
2.7 s
2K prompt

Where the memory goes

Model
195 GB
Context
30.0 GB
Overhead
1.0 GB
OS
15.4 GB
Free
14.2 GB
Memory
242 GB of 256 GB
Context
96K tokens · auto
Speed
12 tok/s · 4.0 when full
First reply
2.7 s for a 2K prompt
Running cost
$3.15/mo at home · $574/mo on a cloud 8× A40

Validation: Validated with conditions

What Hy3 on Dual DGX Spark was checked against
CheckTargetResultStatus
Fits in GPU memory241 GB usable226 GB neededPass
Headroom5% free14.2 GB free (6%)Pass
Context for chat16K or more96KPass
Writing speed15 tok/s or more12 tok/sCheck
First replyunder 3 s, 2K prompt2.7 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
Hy3
Parameters
295B, 21B active
Precision
5-bit (Q5_K_M)
Context
96K, 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
$574/mo
8× A40 at $4.72/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 bartowski/Hy3-GGUF
vLLM
vllm serve tencent/Hy3
MLX (Mac)
mlx_lm.chat --model mlx-community/Hy3-OptiQ-2bit

Hy3 on similar machines

All machines: Hy3 VRAM requirements. Everything that runs here: what can the Dual DGX Spark run?

Other models that run on Dual DGX Spark

Questions

Can Hy3 run on Dual DGX Spark?

Hy3 at 5-bit runs on the DGX Spark 128 GB with 96K of context at about 12 tokens a second.

Report VR-0T6KZS3, calculated Nov 22, 2026 from published specs, not benchmarked.