Runs on a private AI box you own
One compact GB10-class device — 128 GB unified memory — runs it on-premise, sold and provisioned by us. No cloud API keys, no data leaving the building.
Run Phi-4 on-premises
○ Memory-fit arithmetic — checkable math, not a deployment claim
Phi-4 is Microsoft's 14-billion-parameter model under the permissive MIT license, known for strong math and reasoning relative to its size. Its tiny memory footprint makes it a natural choice for multi-model boxes and high concurrency.
Here is the arithmetic on a 128 GB unit.
Memory fit on a 128 GB unit
| Parameters | 14B (dense) |
|---|---|
| 4-bit weights | ~8 GB |
| Device memory | 128 GB unified (one unit) |
| Left for context + other models | roughly 110 GB |
| Units required | 1 (many can co-reside) |
At ~8 GB Phi-4 barely dents the box — you can run several instances or pair it with much larger models on the same unit.
What it serves well
- Math, logic, and structured-reasoning tasks at low cost.
- High-concurrency serving and multi-model deployments.
- A permissive-licensed workhorse for extraction, routing, and tools.
Honest limits
- Arithmetic, not our measured deployment.
- A 14B model is not a flagship — for the broadest general knowledge we would route to a larger model, which the same box can also hold.
Frequently asked questions
- How small is Phi-4 on the box?
- About 8 GB at 4-bit — roughly 110 GB of the 128 GB stays free for context and other models.
- License?
- MIT — permissive and commercial-friendly.
- What is it good at?
- Math and structured reasoning relative to its size; we test it against your specific tasks in the assessment.