Expired80% confidenceFactTime unknown
In an offline test across three phones, the iQOO 15 ran the Gemma 4 1/2B model at the fastest speed.
1
Sources
80%
Confidence
Medium-term (~90 days)
Relevance
6/3/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 9/1/2026(expired)
Sources
Related Entities
Related Claims
UnverifiedIn a local inference speed comparison, Agent A1 (95 tokens/second) was faster than Gemma 4 Coder and the Qwen series.64% similarUnverifiedThe MiniCPM series achieves performance close to 7B and even 13B models on multiple benchmarks with a parameter count at the 2B–4B level61% similarUnverifiedThe Raspberry Pi 5 paired with quantized models can run language models at the 3B parameter level, while the NVIDIA Jetson Orin series with up to 275 TOPS of AI compute can run 7B or even 13B quantized models with latency controllable within 1 second58% similarUnverifiedClaude Haiku 4.5 achieved the fastest generation speed and lowest cost across the three front-end test scenarios.58% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/38373API
curl https://kongchang.com/api/v1/knowledge/claims/38373MCP
get_claim(id=38373)