Skip to content

Llama 3.3 70B on DGX Spark: VRAM, speed and fit

Llama 3.3 70B at 8-bit runs on the DGX Spark 128 GB with 128K of context at about 2.6 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
118 GB
of 128 GB
Context
128K
auto
Speed
2.6 tok/s
1.6 when full
First reply
4.8 s
2K prompt

Where the memory goes

Model
69.8 GB
Context
40.0 GB
Overhead
763 MB
OS
7.7 GB
Free
9.8 GB
Memory
118 GB of 128 GB
Context
128K tokens · auto
Speed
2.6 tok/s · 1.6 when full
First reply
4.8 s for a 2K prompt
Running cost
$3.15/mo at home · $287/mo on a cloud 4× A40

Validation: Not validated

What Llama 3.3 70B on DGX Spark was checked against
CheckTargetResultStatus
Fits in GPU memory120 GB usable111 GB neededPass
Headroom5% free9.8 GB free (8%)Pass
Context for chat16K or more128KPass
Writing speed15 tok/s or more2.6 tok/sFails
First replyunder 3 s, 2K prompt4.8 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
Llama 3.3 70B
Parameters
70.5B
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
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 21, 2026.

How to run it

Ollama
ollama run llama3.3:70b
llama.cpp
llama-server -hf unsloth/Llama-3.3-70B-Instruct-GGUF
vLLM
vllm serve meta-llama/Llama-3.3-70B-Instruct
MLX (Mac)
mlx_lm.chat --model mlx-community/Llama-3.3-70B-Instruct-4bit

Llama 3.3 70B on similar machines

All machines: Llama 3.3 70B VRAM requirements. Everything that runs here: what can the DGX Spark run?

Other models that run on DGX Spark

Questions

Can Llama 3.3 70B run on DGX Spark?

Llama 3.3 70B at 8-bit runs on the DGX Spark 128 GB with 128K of context at about 2.6 tokens a second.

Report VR-1AONR95, calculated Nov 22, 2026 from published specs, not benchmarked.