GGUF-IQ-Imatrix experimental quants for dreamgen/opus-v1.2-llama-3-8b.

This will have to uploaded again later.

Using a different testing config to avoid some reported issues so far and to get through the imatrix data generation.
This is experimental. Proper support and fixes should be coming in the respective projects in due time.

Downloads last month
195
GGUF
Model size
8.03B params
Architecture
llama

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Inference API
Unable to determine this model's library. Check the docs .