Skip to content

Conversation

@b4rtaz
Copy link
Owner

@b4rtaz b4rtaz commented Aug 20, 2025

RTX 3090 24GB, AMD EPYC 7313 16-Core Processor

Prediction (--steps 128)

Model Tokens/s (version 0.15.1) Tokens/s (version 0.15.2) Tokens/s (version 0.15.3) Tokens/s (This PR)
llama3_1_8b_instruct_q40 24.80 24.80 33.32 45.33
image

@b4rtaz b4rtaz merged commit b9ec995 into main Aug 20, 2025
3 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants