Elias Limouni
Eliaccess
·
AI & ML interests
IoT, Deep Learning & Optimization
Recent Activity
Reacted to
csabakecskemeti's
post
with 👍
3 days ago
The AMD Instinct MI50 (~$110) is surprisingly fast for inference Quantized models.
This runs a Llama 3.1 8B Q8 with Llama.cpp
https://huggingface.co/spaces/DevQuasar/Mi50
A little blogpost about the HW
http://devquasar.com/uncategorized/amd-radeon-instinct-mi50-cheap-inference/
Organizations
models
None public yet
datasets
None public yet