23.4 GB

Ctrl+K

1 contributor

Card: Usage now gives the runner settings that load these decode-only bundles (llm-runner sequential engine with one-token prefill, CoreAIKit ChatSession), checked 2026-10-02; drop the stock-pipelined-engine claim

f4ca37d verified 3 days ago

gpu-pipelined
gemma4_12b_qat_decode_int4linsym_msdpa_g8: re-save with coreai-core 1.0.0b2 (strip debug locations; weights unchanged). The 0.4.0-era IR refused AIModel.load on every OS 27 build since beta 2, still on the RC 26A428 (2026-09-14); the re-saved bundle loads. Recovery: coreai-model-zoo conversion/recovery/{strip_b1,resave_b2}.py 21 days ago
.gitattributes

2.3 kB
Gemma 4 12B: gemma4_12b_qat_decode_int4linsym_msdpa_g8 (higher-occupancy decode bundle) 4 months ago
LICENSE

633 Bytes
Gemma 4 12B: Gemma Terms of Use 4 months ago
README.md

9.64 kB
Card: Usage now gives the runner settings that load these decode-only bundles (llm-runner sequential engine with one-token prefill, CoreAIKit ChatSession), checked 2026-10-02; drop the stock-pipelined-engine claim 3 days ago
config.json

307 Bytes
Add config.json so the Hub can count downloads about 2 months ago