Qualcomm AI 100 Ultra
Data center GPU · Cloud AI 100
Summary
Qualcomm's AI 100 Ultra accelerator is a power-efficient chip aimed at LLM inference.
For a cheaper, less powerful accelerator with a similar architecture, see the Qualcomm AI 100 Pro.
Tech specs
VRAM 128 GB LPDDR4x
Memory bandwidth 584 GB/s
Interface PCIe
TDP 150 W
Supported data types
FP16INT8
Cloud rental prices
1 provider · lowest price per GPU, per hour
Reserved
$5.15 – $6.44 /GPU/h
| Provider | On-demand | Reserved | Spot |
|---|---|---|---|
 Cirrascale | — | $5.15 | — |
Models that fit in VRAM
| Total VRAM | From | 16-bit inference | 8-bit inference | 4-bit inference | |
|---|---|---|---|---|---|
| 8× AI 100 Ultra | 1,024 GB | $41.19/h | | | |
Open-weights models that fit in VRAM. Estimated using 🤗 accelerate, plus approximation for up to 8K context.
Media
Resources
Detailed documentation from the manufacturer.
Similar GPUs
Other accelerators you might compare.