Qwen3.8-27B reportedly runs at about 90 tokens per second on a four-year-old AMD GPU over USB
tinygrad says its small size and pure-Python code make it particularly easy to build on.
TLDR
tinygrad claims Qwen3.8-27B runs at about 90 tokens per second on a four-year-old AMD GPU over USB. It also says tinygrad’s small size and pure-Python code make it easy to build on.
Combined views
6.5K
1 Source, first seen 1h ago
94 likes