29 days ago
-
gen-cards: regenerate Use-it block
30 days ago
-
gen-cards: regenerate Use-it block
-
Card: macOS/iOS 27 GA wording (beta requirement dropped; beta findings dated)
-
gen-cards: regenerate Use-it block
-
Card: DeviceMark row (2026-09)
-
Card metadata: library_name coreai, ensure coreai tag
-
Card: definition line (Core AI, 2026-09)
-
Card: base_model_relation: quantized (so the conversion lists under the base model's Quantizations, not Finetunes)
-
gen-cards: regenerate Use-it block
-
Link the card back to its collection and the request box
-
gen-cards: regenerate Use-it block
-
Re-export with coreai-torch 0.4.1 (fixes OS 27 beta 2+ load failure); gated token-for-token vs fp32 oracle
-
gen-cards: regenerate Use-it block
-
gen-cards: add Use-it markers
-
ship Mac-only: card reflects sym8 (clean) only; int4 not shipped
-
ship Mac-only: remove iPhone int4 (quality not at bar; runs but degraded)
-
remove int8km (k-means int8) — superseded by clean sym8
-
LFM2.5-8B-A1B: sym8 (clean linear int8) Mac bundle
-
LFM2.5-8B-A1B: honest sym8 card (clean Mac int8)
-
LFM2.5-8B-A1B: int4km (iPhone-jetsam-safe, runs on device) decode-pipelined bundle
-
LFM2.5-8B-A1B: int8km (Mac, 141 tok/s) decode-pipelined bundle
-
LFM2.5-8B-A1B: config (download counting)
-
LFM2.5-8B-A1B: LFM Open License v1.0
-
LFM2.5-8B-A1B: model card
-
initial commit
