Qualcomm AI 100 Pro

Name: Qualcomm AI 100 Pro
Brand: Qualcomm
Availability: InStock

Data center GPU · Cloud AI 100

Summary

Qualcomm's AI 100 Pro accelerator is a low-power chip aimed at LLM inference.

For a more powerful accelerator with a similar architecture, see the Qualcomm AI 100 Ultra.

Launched

2024

VRAM

32 GB

Mem. bandwidth

137 GB/s

On-demand from

Tech specs

VRAM 32 GB LPDDR4x

Memory bandwidth 137 GB/s

Interface PCIe

TDP 75 W

Supported data types

FP16INT8

2 providers · available in 2 countries · lowest price per GPU, per hour

Prices updated 28 July 2026

On-demand

$1.11 /GPU/h

Reserved

$0.35 – $3.42 /GPU/h

Provider	On-demand	Reserved	Spot
AWS	$1.11	$0.48	—
Cirrascale	—	$0.35	—

	Total VRAM	From	16-bit inference	8-bit inference	4-bit inference
1× AI 100 Pro	32 GB	$0.35/h	Qwen3-4B-Instruct-2507Rio-3.0-Open-MiniNVIDIA-Nemotron-3-Nano-4B-BF16	gpt-oss-20bQwen3-4B-Instruct-2507Rio-3.0-Open-Mini	GLM-4.7-FlashQwen3-Coder-30B-A3B-InstructNVIDIA-Nemotron-3-Nano-30B-A3B-BF16
2× AI 100 Pro	64 GB	$1.42/h	gpt-oss-20bQwen3-4B-Instruct-2507Rio-3.0-Open-Mini	GLM-4.7-FlashQwen3-Coder-30B-A3B-InstructNVIDIA-Nemotron-3-Nano-30B-A3B-BF16	GLM-4.5-AirQwen3-Coder-NextNVIDIA-Nemotron-3-Nano-30B-A3B-BF16
4× AI 100 Pro	128 GB	$5.53/h	GLM-4.7-FlashQwen3-Coder-30B-A3B-InstructNVIDIA-Nemotron-3-Nano-30B-A3B-BF16	GLM-4.5-AirQwen3-Coder-NextNVIDIA-Nemotron-3-Nano-30B-A3B-BF16	DeepSeek-V4-Flashgpt-oss-120bNVIDIA-Nemotron-3-Super-120B-A12B-BF16
8× AI 100 Pro	256 GB	$3.85/h	GLM-4.5-AirQwen3-Coder-NextNVIDIA-Nemotron-3-Nano-30B-A3B-BF16	MiniMax-M2.7DeepSeek-V4-Flashgpt-oss-120b	MiniMax-M2.7DeepSeek-V4-Flashgpt-oss-120b

Show all configurations

Open-weights models that fit in VRAM. Estimated using 🤗 accelerate, plus approximation for up to 8K context.

Detailed documentation from the manufacturer.

Other accelerators you might compare.