grug 1: qwen3 GGUF inference but is da nimrod
grug 2: wow nimpressive
Fast and efficient Nim inference for Qwen3 GGUF with the smallest (0.6B) at the fullest (FP32)
Inspired by and a (near) faithful translation of qwen3.c
bkataru-workshop/qwen3.nim
Folders and files
| Name | Name | Last commit date | ||
|---|---|---|---|---|