Unverified50% confidenceFactExact time
Phone SoCs typically have several GB of memory and tens of TOPS of NPU computing power, three to four orders of magnitude apart from microcontrollers such as the RP2350.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/30/2026
First Seen
Valid until: 1/28/2027
Sources
Related Entities
Related Claims
UnverifiedLocal inference is constrained by the user's hardware: a 7B-parameter quantized model (such as the Q4 version of Llama 3 8B) has a file size of approximately 4–5 GB, can reach 20–40 tokens per second on a Mac with an Apple M-series chip, and may drop to 3–5 tokens per second on a laptop with only an integrated GPU and 8 GB of RAM.69% similarUnverifiedThe iOS export uses Core ML 8-bit weights, with a model size of 26MB and 99.96% agreement with fp32 labels, and in the keyboard it actually uses the CPU compute unit, taking about 4ms per sentence in a release build; the Android version uses ONNX opset 17 with int8 dynamic quantization, 27MB, 99.1% agreement, and likewise about 4ms per sentence on CPU.69% similarUnverifiedCerebras WSE-3片上内存高达44GB SRAM，带宽达到21 PB/s，比GPU的HBM内存快约1000倍69% similarUnverifiedA developer connected an iPhone 17 Pro Max to a 24GB-memory M4 Pro MacBook via a 10 Gb/s USB-C cable, using the phone as a second GPU to share the computational load for a locally running Qwen 3.8 27B (IQ4_XS quantization) model.69% similarUnverifiedThe hardware gap between phones and servers: phone memory is 12 to 16GB (servers about 80GB), phone bandwidth is 50 to 80GB (servers are in the TB range), and power constraints are stricter.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1117589API
curl https://kongchang.com/api/v1/knowledge/claims/1117589MCP
get_claim(id=1117589)