Skip to content

Conversation

@phueper
Copy link

@phueper phueper commented Nov 5, 2025

I find that somewhat easier to compare stats for multiple models:

output looks like this then:

Evaluating models: ['llama3:latest', 'gemma3:4b']

Table stats:
| Model         |            Prompt |   Evaluation |   Total |   Load Time |             Prompt |            Prompt |   Evalutaion |   Evaluation |   Total Time |
| Name          |   Evaluation Rate |         Rate |    Rate |         (s) |   Evaluation Count |   Evaluation Time |        Count |         Time |          (s) |
|               |             (T/s) |        (T/s) |   (T/s) |             |                    |               (s) |              |          (s) |              |
|---------------+-------------------+--------------+---------+-------------+--------------------+-------------------+--------------+--------------+--------------|
| llama3:latest |            413.58 |        45.55 |   48.41 |        1.14 |                 33 |              0.08 |          463 |        10.17 |        11.56 |
| gemma3:4b     |            468.31 |        64.62 |   66.06 |        1.92 |                 31 |              0.07 |         1190 |        18.42 |        20.72 |

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.

1 participant