ViewTube

ViewTube
Sign inSign up
Filters

Upload date

Type

Duration

Sort by

Features

Reset

2 results

Code Unpacked
Strata Just Beat llama.cpp on a 12GB GPU

The same Qwen3.8-Flash-Next file on the same 12 GB RTX 3060: 9.1 tokens per second on llama.cpp, 41.6 on Strata. You asked ...

13:03
Strata Just Beat llama.cpp on a 12GB GPU

4,366 views

12h ago

Code Unpacked
llama.cpp Just Made Huge MoE Models 4× Faster

The same Radeon GPU, the same Qwen model, no new quantization trick: 9.7 tokens per second became 37.2. llama.cpp already ...

9:15
llama.cpp Just Made Huge MoE Models 4× Faster

17,026 views

5d ago