github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-08 17:49:24 -05:00
Code Issues 14.6k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #10857] num_predict parameter does not work ? #53644

New Issue
Closed
opened 2026-04-29 04:21:54 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-29 04:21:54 -05:00
Owner
Copy Link

Originally created by @zswodegit on GitHub (May 26, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/10857

What is the issue?

hi,
Im trying to test ollama performance like ttft, latency etc.. with qwen model. I couldnt find any related instruction on repository main page, so i trying to modify some parameter during the inference: setting num_predict=1 to test the ttft, but it does not work at all. do you know whats the problem is?

Image

Relevant log output

url = "http://localhost:11434/api/generate"
headers = {"Content-Type": "application/json"}
data = {"model":"qwenvl", "prompt":"say something", "num_predict": 1, "stream": True}
res = requests.post(url, headers=headers, json=data)

OS

Linux

GPU

Nvidia

CPU

No response

Ollama version

ollama=0.7.0

Originally created by @zswodegit on GitHub (May 26, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/10857 ### What is the issue? hi, Im trying to test ollama performance like ttft, latency etc.. with qwen model. I couldnt find any related instruction on repository main page, so i trying to modify some parameter during the inference: setting `num_predict=1` to test the ttft, but it does not work at all. do you know whats the problem is? ![Image](https://github.com/user-attachments/assets/6c3cde16-68a9-46dd-b53c-432ae4684ee5) ### Relevant log output ```shell url = "http://localhost:11434/api/generate" headers = {"Content-Type": "application/json"} data = {"model":"qwenvl", "prompt":"say something", "num_predict": 1, "stream": True} res = requests.post(url, headers=headers, json=data) ``` ### OS Linux ### GPU Nvidia ### CPU _No response_ ### Ollama version ollama=0.7.0
GiteaMirror added the bug label 2026-04-29 04:21:54 -05:00
GiteaMirror commented 2026-04-29 04:22:03 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (May 26, 2025):

num_predict goes in the options field.

$ curl localhost:11434/api/generate -d '{"model":"qwen2.5:0.5b","prompt":"say something","options":{"num_predict":1}}'
{"model":"qwen2.5:0.5b","created_at":"2025-05-26T07:36:26.888672145Z","response":"Hello","done":false}
{"model":"qwen2.5:0.5b","created_at":"2025-05-26T07:36:26.888676576Z","response":"","done":true,"done_reason":"length","context":[151644,8948,198,2610,525,1207,16948,11,3465,553,54364,14817,13,1446,525,264,10950,17847,13,151645,198,151644,872,198,36790,2494,151645,198,151644,77091,198,9707],"total_duration":353061979,"load_duration":336888958,"prompt_eval_count":31,"prompt_eval_duration":11179534,"eval_count":1,"eval_duration":3387738}
<!-- gh-comment-id:2908849505 --> @rick-github commented on GitHub (May 26, 2025): `num_predict` goes in the `options` field. ```console $ curl localhost:11434/api/generate -d '{"model":"qwen2.5:0.5b","prompt":"say something","options":{"num_predict":1}}' {"model":"qwen2.5:0.5b","created_at":"2025-05-26T07:36:26.888672145Z","response":"Hello","done":false} {"model":"qwen2.5:0.5b","created_at":"2025-05-26T07:36:26.888676576Z","response":"","done":true,"done_reason":"length","context":[151644,8948,198,2610,525,1207,16948,11,3465,553,54364,14817,13,1446,525,264,10950,17847,13,151645,198,151644,872,198,36790,2494,151645,198,151644,77091,198,9707],"total_duration":353061979,"load_duration":336888958,"prompt_eval_count":31,"prompt_eval_duration":11179534,"eval_count":1,"eval_duration":3387738} ```
GiteaMirror commented 2026-04-29 04:22:11 -05:00
Author
Owner
Copy Link

@zswodegit commented on GitHub (May 27, 2025):

num_predict goes in the options field.

$ curl localhost:11434/api/generate -d '{"model":"qwen2.5:0.5b","prompt":"say something","options":{"num_predict":1}}'
{"model":"qwen2.5:0.5b","created_at":"2025-05-26T07:36:26.888672145Z","response":"Hello","done":false}
{"model":"qwen2.5:0.5b","created_at":"2025-05-26T07:36:26.888676576Z","response":"","done":true,"done_reason":"length","context":[151644,8948,198,2610,525,1207,16948,11,3465,553,54364,14817,13,1446,525,264,10950,17847,13,151645,198,151644,872,198,36790,2494,151645,198,151644,77091,198,9707],"total_duration":353061979,"load_duration":336888958,"prompt_eval_count":31,"prompt_eval_duration":11179534,"eval_count":1,"eval_duration":3387738}

it works thanks!

<!-- gh-comment-id:2910960252 --> @zswodegit commented on GitHub (May 27, 2025): > `num_predict` goes in the `options` field. > > $ curl localhost:11434/api/generate -d '{"model":"qwen2.5:0.5b","prompt":"say something","options":{"num_predict":1}}' > {"model":"qwen2.5:0.5b","created_at":"2025-05-26T07:36:26.888672145Z","response":"Hello","done":false} > {"model":"qwen2.5:0.5b","created_at":"2025-05-26T07:36:26.888676576Z","response":"","done":true,"done_reason":"length","context":[151644,8948,198,2610,525,1207,16948,11,3465,553,54364,14817,13,1446,525,264,10950,17847,13,151645,198,151644,872,198,36790,2494,151645,198,151644,77091,198,9707],"total_duration":353061979,"load_duration":336888958,"prompt_eval_count":31,"prompt_eval_duration":11179534,"eval_count":1,"eval_duration":3387738} it works thanks!
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 bug
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#53644
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?