Download Latest Version
0.16.3 source code.tar.gz (1.3 MB)
Get an email when there's a new version of Distributed Llama
| Name | Modified | Size | Downloads / Week |
|---|---|---|---|
| Parent folder | |||
| 0.16.0 source code.tar.gz | 2025-09-05 | 1.3 MB | |
| 0.16.0 source code.zip | 2025-09-05 | 1.4 MB | |
| README.md | 2025-09-05 | 327 Bytes | |
| Totals: 3 Items | 2.7 MB | 0 | |
This version adds support for Qwen3 MOE models on CPU. Vulkan support will be added in a future release.
The performance of MOE models is quite impressive: Qwen3-30B-A3B-Q40 achieves 13.04 tok/s during evaluation on 4× Raspberry Pi 5 (8GB). Check details here.
