ryugyosoft
/

onwx

inference-engine

Model card Files Files and versions

onwx / tools

120 kB

Ctrl+K

Ctrl+K

1 contributor

History: 7 commits

ryugyosoft's picture

onwx 1.0.0: LFM2.5 24B-A2B (converted on your PC, two-block int4, chunked prompts ~430 tok/s)

e0b7fb9 verified 14 days ago

glue_cpu
onwx 0.9.0: Qwen3.6 35B-A3B experts from the SSD (~7 GB of memory), images, faster MTP; changelog shown with updates 19 days ago
lfx_glue
onwx 1.0.0: LFM2.5 24B-A2B (converted on your PC, two-block int4, chunked prompts ~430 tok/s) 14 days ago
xdna_shim
onwx 0.8.0: Qwen3.6 35B-A3B (MoE, int4, all on the NPU: ~20 tok/s, ~22 with MTP; prompts 1K 3.1 s vs FLM 10.2 s), MoE host steps in C 19 days ago