[GH-ISSUE #8367] Single json expected when streaming set to false #5368

Closed
opened 2026-04-12 16:34:50 -05:00 by GiteaMirror · 2 comments
Owner

Originally created by @gklcbord on GitHub (Jan 9, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/8367

What is the issue?

Trying the API with this input json:

{
"model": "llama3.2",
"prompt": "Why is the sky blue?",
"streaming": false
}

and I am getting return similar to below:
{
"model": "llama3.2",
"created_at": "2025-01-09T19:31:13.2233009Z",
"response": "The",
"done": false
}
{
"model": "llama3.2",
"created_at": "2025-01-09T19:31:13.3150935Z",
"response": " sky",
"done": false
}
{
"model": "llama3.2",
"created_at": "2025-01-09T19:31:13.4029015Z",
"response": " appears",
"done": false
}
....

How do I get a single json? It behaves the same no matter what model I use.

Unrelated issue:
Sometime models I get error saying they aren't loaded but I see them when I do "ollama list". For e.g. "qwen2.5-coder", "granite3.1-moe" come back with an error:

"{
"error": "model 'granite3.1-moe' not found"
}"

OS

Windows

GPU

Other

CPU

Intel

Ollama version

0.5.4

Originally created by @gklcbord on GitHub (Jan 9, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/8367 ### What is the issue? Trying the API with this input json: { "model": "llama3.2", "prompt": "Why is the sky blue?", "streaming": false } and I am getting return similar to below: { "model": "llama3.2", "created_at": "2025-01-09T19:31:13.2233009Z", "response": "The", "done": false } { "model": "llama3.2", "created_at": "2025-01-09T19:31:13.3150935Z", "response": " sky", "done": false } { "model": "llama3.2", "created_at": "2025-01-09T19:31:13.4029015Z", "response": " appears", "done": false } .... How do I get a single json? It behaves the same no matter what model I use. Unrelated issue: Sometime models I get error saying they aren't loaded but I see them when I do "ollama list". For e.g. "qwen2.5-coder", "granite3.1-moe" come back with an error: "{ "error": "model 'granite3.1-moe' not found" }" ### OS Windows ### GPU Other ### CPU Intel ### Ollama version 0.5.4
GiteaMirror added the bug label 2026-04-12 16:34:50 -05:00
Author
Owner

@rick-github commented on GitHub (Jan 9, 2025):

stream, not streaming.

<!-- gh-comment-id:2581298019 --> @rick-github commented on GitHub (Jan 9, 2025): `stream`, not `streaming`.
Author
Owner

@gklcbord commented on GitHub (Jan 10, 2025):

stream, not streaming.

Thanks! that worked!

For the second issue I mentioned, it seems like I need to include the full name if not latest. For e.g. "smollm2:latest" doesn't need ":latest" to be included but "qwen2.5-coder:32b" does need ":32b" to be included for it to work.

<!-- gh-comment-id:2582884776 --> @gklcbord commented on GitHub (Jan 10, 2025): > `stream`, not `streaming`. Thanks! that worked! For the second issue I mentioned, it seems like I need to include the full name if not latest. For e.g. "smollm2:latest" doesn't need ":latest" to be included but "qwen2.5-coder:32b" does need ":32b" to be included for it to work.
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#5368