How many users can one GB10 serve at the same time?
How many users can one GB10 serve at the same time?
Rentable machine
Solved NVIDIA DGX Spark (GB10)
dgx-spark
- Views
- 0
- Replies
- 5
- Created
- 2026-06-30 11:00
- Last reply
- 2026-06-30 21:25
There is no useful single number for that.
It depends on the model, context length, output length, batching, quantization and what latency you consider acceptable.
A 7B model and a 30B dense model can differ massively even on the same GB10.
Give us the model plus average prompt/output sizes and target requests per minute. Then we can load-test or estimate it.
Without those numbers, any 'users per GB10' figure would be marketing rather than capacity planning.
Sign in to reply.
Posting guidelines
- Be helpful and respectful
- Search before you post
- Use a clear title and tags
- Add code or a screenshot when it helps
- Keep to the topic
Accounts that break these can lose forum access — paid plans included. Read the full guidelines →
Related topics
- GPU and machine requests — ask for one we don't have yet 0 replies · 2 views
- Can I run Windows on a rented GB10? 3 replies · 1 views
- Which GPU is better for image generation? 3 replies · 1 views
- Can one model use all four RTX 5090s? 3 replies · 1 views
- Will my normal Docker containers run on a GB10? 3 replies · 1 views