github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #1960] Feature Request : new flag of --benchmark #1130

New Issue
Open
opened 2026-04-12 10:52:28 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-12 10:52:28 -05:00
Owner
Copy Link

Originally created by @vincecate on GitHub (Jan 12, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/1960

We are making a website for performance results using different hardware running ollama models at http://LLMPerformance.ai

It would be really helpful if ollama had a flag "--benchmark" which made it output everything that "--verbose" does
but also added the following info:

CPU:
Memory:
GPU:
VRAM:
LLM Model Name:
LLM Model Layers on GPU:
Total Model Layers:
Ollama Version:
Operating System:
Date:

The names etc don't matter as long as it is clear.
This will help make sure that reported results have enough info to be reproducible.

Originally created by @vincecate on GitHub (Jan 12, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/1960 We are making a website for performance results using different hardware running ollama models at http://LLMPerformance.ai It would be really helpful if ollama had a flag "--benchmark" which made it output everything that "--verbose" does but also added the following info: CPU: Memory: GPU: VRAM: LLM Model Name: LLM Model Layers on GPU: Total Model Layers: Ollama Version: Operating System: Date: The names etc don't matter as long as it is clear. This will help make sure that reported results have enough info to be reproducible.
GiteaMirror commented 2026-04-12 10:52:29 -05:00
Author
Owner
Copy Link

@chuangtc commented on GitHub (Apr 1, 2024):

There is a tool working towards this. Please advice how to merge our efforts on creating such tool.
https://llm.aidatatools.com/
It's called llm-benchmark

pip install llm-benchmark
llm_benchmark run
<!-- gh-comment-id:2029476830 --> @chuangtc commented on GitHub (Apr 1, 2024): There is a tool working towards this. Please advice how to merge our efforts on creating such tool. https://llm.aidatatools.com/ It's called llm-benchmark ```bash pip install llm-benchmark llm_benchmark run ```
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#1130
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?