github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #14716] qwen3.5 vision output routes to thinking field instead of content when using image inputs #35274

New Issue
Closed
opened 2026-04-22 19:40:07 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-22 19:40:07 -05:00
Owner
Copy Link

Originally created by @souhailchenaoua on GitHub (Mar 8, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/14716

What is the issue?

When sending image inputs to qwen3.5 models via ollama.chat(), all output is routed to response.message.thinking and response.message.content is always empty. Text-only inputs work correctly. Setting thinking: False in options has no effect when images are involved.

Relevant log output

**To Reproduce**

import ollama

with open("page.png", "rb") as f:
    img_bytes = f.read()

response = ollama.chat(
    model="qwen3.5:9b",
    messages=[{"role": "user", "content": "Describe this image.", "images": [img_bytes]}],
    options={"temperature": 0.7, "top_p": 0.80, "top_k": 20, "thinking": False},
)

print("content:", repr(response.message.content))   # always empty
print("thinking:", repr(response.message.thinking)) # full output here


**Expected:** response.message.content contains the model's response
**Actual:** response.message.content is empty, full output in response.message.thinking

OS

Windows

GPU

Nvidia

CPU

Intel

Ollama version

0.17.4

Originally created by @souhailchenaoua on GitHub (Mar 8, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/14716 ### What is the issue? When sending image inputs to qwen3.5 models via ollama.chat(), all output is routed to response.message.thinking and response.message.content is always empty. Text-only inputs work correctly. Setting thinking: False in options has no effect when images are involved. ### Relevant log output ```shell **To Reproduce** import ollama with open("page.png", "rb") as f: img_bytes = f.read() response = ollama.chat( model="qwen3.5:9b", messages=[{"role": "user", "content": "Describe this image.", "images": [img_bytes]}], options={"temperature": 0.7, "top_p": 0.80, "top_k": 20, "thinking": False}, ) print("content:", repr(response.message.content)) # always empty print("thinking:", repr(response.message.thinking)) # full output here **Expected:** response.message.content contains the model's response **Actual:** response.message.content is empty, full output in response.message.thinking ``` ### OS Windows ### GPU Nvidia ### CPU Intel ### Ollama version 0.17.4
GiteaMirror added the bug label 2026-04-22 19:40:07 -05:00
GiteaMirror commented 2026-04-22 19:40:09 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Mar 8, 2026):

--- 14716.py.orig       2026-03-08 15:44:54.292964092 +0100
+++ 14716.py    2026-03-08 15:47:45.360179340 +0100
@@ -6,7 +6,8 @@
 response = ollama.chat(
     model="qwen3.5:9b",
     messages=[{"role": "user", "content": "Describe this image.", "images": [img_bytes]}],
-    options={"temperature": 0.7, "top_p": 0.80, "top_k": 20, "thinking": False},
+    options={"temperature": 0.7, "top_p": 0.80, "top_k": 20},
+    think=False
 )

 print("content:", repr(response.message.content))   # always empty
<!-- gh-comment-id:4019187358 --> @rick-github commented on GitHub (Mar 8, 2026): ```diff --- 14716.py.orig 2026-03-08 15:44:54.292964092 +0100 +++ 14716.py 2026-03-08 15:47:45.360179340 +0100 @@ -6,7 +6,8 @@ response = ollama.chat( model="qwen3.5:9b", messages=[{"role": "user", "content": "Describe this image.", "images": [img_bytes]}], - options={"temperature": 0.7, "top_p": 0.80, "top_k": 20, "thinking": False}, + options={"temperature": 0.7, "top_p": 0.80, "top_k": 20}, + think=False ) print("content:", repr(response.message.content)) # always empty ```
GiteaMirror commented 2026-04-22 19:40:10 -05:00
Author
Owner
Copy Link

@Sasha-BabyBird commented on GitHub (Mar 9, 2026):

You may want to set num_predict to a large value when enabling thinking and providing images to input.

<!-- gh-comment-id:4024153397 --> @Sasha-BabyBird commented on GitHub (Mar 9, 2026): You may want to set num_predict to a large value when enabling thinking and providing images to input.
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#35274
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?