Idle or always-on
Choose how consistently the selected infrastructure contributes.
Company Providers
Your infrastructure.A broader purpose.
Bring eligible organizational compute to ShareAI. Configure supported models, manage devices and choose contribution modes around your operating needs.
Eligible compute. Your availability. Your contribution.
Personal compute
Company infrastructure
Eligible capacitySupported models
ShareAI networkContribute when available
Idle-timeAlways-on
CHOOSE AN AVAILABLE PATHRewards · Exchange · Mission
01
CheckReview device eligibility
02
ConnectSet up supported serving
03
ChoosePick your contribution mode
04
TrackReview activity and incentives
The part worth solving
Capacity and demand rarely line up perfectly.
Organizations need to decide which infrastructure can participate, when it is available and who will operate the offering.
A clearer model
Make contribution an operating decision.
Start with eligible capacity, supported onboarding and clear availability. Explore applicable Rewards, Exchange or Mission programs without assuming a fixed return.
Where it fits
A contribution that fits your setup.
Operational ownership
Manage devices, model support and availability through the Provider workspace.
Company prosuming
Explore contributing compute and using AI as two parts of your company’s participation.
Choose your motivation
Three ways to put compute to work.
Explore the incentive paths available to eligible Providers. Review the applicable program and device requirements in your Provider workspace.
Money where available
Explore earnings from eligible compute.
Rewards is the monetary incentive path for eligible capacity contributed to the network where available. Review its terms and attributed activity; a connected machine is not a guaranteed income.
Eligible compute contributionProvider Rewards
- Contribution
- Compute supplied to the network
- Value
- Money under applicable Rewards terms
- Availability
- Subject to eligibility and program support
AI usage value
Contribute capacity. Participate as a prosumer.
Exchange offers tokens or AI usage value for eligible compute contribution where supported. This connects contributing to the network with using AI under the applicable Exchange terms.
Eligible compute contributionTokens or AI usage value
- Contribution
- Eligible capacity in the Exchange program
- Value
- Tokens or AI usage value under its terms
- Availability
- Review supported participation and access
Supported causes
Direct contribution toward a cause.
Choose supported causes where Mission is available. Examples include education, environmental, healthcare, humanitarian and animal welfare initiatives.
Eligible compute contributionA supported Mission
- Contribution
- Capacity directed through an available Mission
- Value
- Participation in a supported cause
- Availability
- Defined by each mission and its requirements
Put your GPU to work
What could your capacity look like?
Choose your GPU, set your rates and find out what a fully booked schedule could be worth.
RTX 3080-based estimateAbout 140 output tokens per second, per GPU.
Up to 24
Model, speed & job load
Reference modelLlama 2 7B · Q4_0
Short requests: 512 input tokens and 128 output tokens. Each GPU handles one request at a time.
Have your own benchmark? Replace both speeds. Selecting another GPU restores its reference values.
100% means requests arrive continuously throughout your selected hours. Lower it to account for idle time.
Published speeds come from community llama.cpp tests with Flash Attention off. The RTX 3080 Ti preset uses an RTX 3080 reference; it is an approximation, not a measured 3080 Ti result.
Input processing and output generation share the same time budget. Real throughput also depends on context, software and request overhead. A month is 30 days, with your weekly schedule repeated.
View benchmark sources$54.28per 30-day month
At 100% job load
Gross estimate, before electricity, fees and taxes.
310.2M input tokens$31.02
77.5M output tokens$23.26
Your weekly schedule40 GPU-hours
Your planned availabilityRest of the day
5 days selected1 GPU × 8 hours × 5 days
This is a synthetic scenario, not a payout offer. Actual serving and Rewards depend on eligibility, demand and program terms. Exchange and Mission have their own incentives.
A practical scenario
A company starts with a defined pool of capacity.
An operations team selects eligible infrastructure, configures supported models and monitors availability before expanding its contribution.
- 01Identify capacity
- 02Assign operators
- 03Configure serving
- 04Review participation
Can any machine become a Provider?
Participation depends on device eligibility and supported configuration. Review the Provider requirements before connecting hardware; no machine is automatically eligible.
Do I need to keep my machine online all the time?
Providers can explore idle-time contribution or always-on contribution. Choose the mode that fits your setup and review availability requirements for the program you select.
Which systems can I use?
Provider onboarding topics include Windows, Ubuntu, macOS and Docker. Review the current instructions for the platform, hardware and serving setup relevant to your device.
Are Rewards, Exchange and Mission the same thing?
They are distinct incentive paths. Rewards offers money where available, Exchange offers tokens or AI usage value, and Mission directs contribution toward supported causes. Applicable terms determine participation.
How do Provider incentives differ from Builder and Creator earnings?
Providers contribute compute. Builders own applications and earn their configured margin on routed AI traffic. Creators own or control model assets and choose their model access terms.
Providers