#on-device AI
5 articles tagged on-device AI. At twelve articles this topic starts lifting the whole site in search.
Timeline
-
Edge0-145B specs — 145 billion parameters in 29GB? The download is 106GB
-
What is an NPU — how it differs from a GPU, and why it wins at inference
-
What an in-house application processor is — why Xiaomi dropped Qualcomm
-
Meta put a 30B agent model on a laptop — Apache 2.0, no server required
All articles
-
Tech · 15 min readEdge0-145B specs — 145 billion parameters in 29GB? The download is 106GB
The arithmetic — fitting all 145 billion parameters in 29GB would take 1.6 bits each. The actual files are a 40GB expert pool plus a 51GB embedding table, about 106GB in total
-
Tech · 3 min readWhat is an NPU — how it differs from a GPU, and why it wins at inference
Definition — a chip for neural-network math only; it trades generality for efficiency
-
Tech · 3 min readWhat an in-house application processor is — why Xiaomi dropped Qualcomm
Definition — the phone's main chip designed by the handset maker; CPU, GPU and AI engine in one package
-
Tech · 3 min readMeta put a 30B agent model on a laptop — Apache 2.0, no server required
Muse Glimmer 30B — distilled from Muse Spark 1.2, weights released under Apache 2.0
-
Tech · 4 min readOn-device AI explained — what changed to let big models run without a server
Memory is the binding constraint — cutting bits per parameter is what puts a 30B model on personal hardware