GPUs / Qualcomm

Adreno 750

Memory
LPDDR5X-9600
Bus
Not published
Published peak
Not published
Capacity
from 8 GB

Measured

Read
53.9GB/s
Write
39.3GB/s
Copy
42.9GB/s
Random
0.28GB/s
Latency
391ns
Sustain
46.6GB/s

Medians of 1 verified run from 1 operator.

Local AI speed

ModelParameters4-bit, tokens/s8-bit, tokens/s
Llama 3.1 8B8.03B≤ 13Does not fit
Qwen 2.5 14B14.7B≤ 7.3Does not fit
gpt-oss-20b21B, 3.6B activeDoes not fitDoes not fit
Mistral Small 24B24BDoes not fitDoes not fit
Qwen 2.5 32B32.5BDoes not fitDoes not fit
Llama 3.3 70B70.6BDoes not fitDoes not fit
gpt-oss-120b117B, 5.1B activeDoes not fitDoes not fit
Upper bounds: median read ÷ bytes read per token. Mixture-of-experts models read only their active experts. Fit checks weights against the smallest 8 GB configuration; the KV cache needs room on top.

Top operators

#OperatorScoreReadDate
1OP-C7555123.553.9 GB/s2026-09-27

Full Adreno 750 leaderboard