Expired50% confidenceBenchmarkExact time
PrismML's Bonsai technology enables a 27B parameter model to run at approximately 11 tokens/second on an iPhone 17 Pro
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/20/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 10/18/2026(expired)
Sources
Related Claims
UnverifiedBonsai 27B is the first 27B-class large model capable of running on a smartphone; through quantization technology, the 54 GB model is compressed to 3.8 GB—a size reduction of approximately 93%—while retaining approximately 90% of its intelligence level, and it can run locally on an iPhone 17 Pro.69% similarUnverifiedOn a 16 GB Mac Mini, Ornith 9B generates at approximately 16 tokens/second for simple requests.61% similarUnverifiedA tester ran a 20.7B dense model on a dual-4090 (48 GB VRAM) workstation and achieved 27.6 tokens per second, only slightly faster than Dwarf Star, but with over 10 times fewer parameters.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/569974API
curl https://kongchang.com/api/v1/knowledge/claims/569974MCP
get_claim(id=569974)