Apple details AFM context sizes; fm serve spins up a local Chat Completions API
rxwei · x · 2026-11-07
Following its Apple Intelligence Group Lab livestream, Apple published a doc on Apple Foundation Models context sizes: AFM Core Advanced (20B params, 8K context, on-device), AFM Core (3B params, 4–8K context, on-device), and AFM Cloud (32K context, Private Cloud Compute).
Practical bonus: the fm CLI lets you chat with the on-device model in the terminal and start a local Chat Completions-compatible API server via fm serve (endpoints /v1/chat/completions, /health, /v1/models; TCP or Unix socket modes) — wiring Apple's on-device model into standard OpenAI-style calls.
More from Infra
- Huawei Ascend 960 roadmap pulled forward up to 3 quarters; analyst says scale-up domain beats efficiency — teortaxesTex · 2026-11-07
- CroissAttn runs all six attention matmuls in FP4 on Blackwell: 1.5× throughput, 55% less memory — TristanThrush · 2026-11-07
- SemiAnalysis: SGLang on AMD Mi355 crushes B200/B300 in throughput test — AnushElangovan · 2026-11-07
- Musk explains Terafab: not 'terror fab' but a terawatt-scale fab — elonmusk · 2026-11-07
- AMD launches free AI Developer Program with cloud credits and ROCm training — AnushElangovan · 2026-11-07
- Musk says data center unpopularity is temporary: Memphis is booming with 2x wages — inductionheads · 2026-11-07