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 #15592] Huge difference in image input tokens with local Qwen3.5 versions when format="json" specified #72010

New Issue
Open
opened 2026-05-05 03:18:26 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-05-05 03:18:26 -05:00
Owner
Copy Link

Originally created by @fchahun on GitHub (Apr 14, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/15592

What is the issue?

With local versions of Qwen3.5 (9b, 27b, 35b, 122b), using a blank prompt and a single image (attached) as input, I notice a huge difference in input tokens depending whether format is unspecified or assigned to "json" (prompt_eval_count increases from 432 to 1789).

This does not occur with the cloud version (397b-cloud) (prompt_eval_count remains unchanged at 432)

This does not occur either with other models such as gemma4 (prompt_eval_count slightly increases from 281 to 286)

This phenomenon can be easily reproduced using the attached image an the curl commands below.

What is the reason for that?

IMG=$(base64 < Image_001.jpeg | tr -d '\n')

echo "{\"model\": \"qwen3.5:27b\", \"messages\": [{\"role\": \"user\",  \"content\": \"\",\"images\": [\"$IMG\"] }],\"stream\": false}" | curl -X POST http://0.0.0.0:11434/api/chat -H "Content-Type:
 application/json" -d @-
{"model":"qwen3.5:27b","created_at":"2026-04-14T12:57:14.954993416Z","message":{"..."},"done":true,"done_reason":"stop","total_duration":160473406601,"load_duration":6219169752,"prompt_eval_count":432,"prompt_eval_duration":724455268,"eval_count":2003,"eval_duration":152220636272}


echo "{\"model\": \"qwen3.5:27b-q4_K_M\", \"messages\": [{\"role\": \"user\",  \"content\": \"\",\"images\": [\"$IMG\"] }],\"stream\": false, \"format\": \"json\"}" | curl -X POST http://0.0.0.0:11434/api/chat -H "Content-Type: application/json" -d @-
{"model":"qwen3.5:27b-q4_K_M","created_at":"2026-04-14T21:27:56.795489648Z","message":{"..."},"done":true,"done_reason":"stop","total_duration":156916654288,"load_duration":8222672080,"prompt_eval_count":1789,"prompt_eval_duration":2405578208,"eval_count":300,"eval_duration":26354827648}

echo "{\"model\": \"qwen3.5:397b-cloud\", \"messages\": [{\"role\": \"user\",  \"content\": \"\",\"images\": [\"$IMG\"] }],\"stream\": false}" | curl -X POST http://0.0.0.0:11434/api/chat -H "Content-Type: application/json" -H "Authorization: Bearer $OLLAMA_API_KEY" -d @-
{"model":"qwen3.5:397b","created_at":"2026-04-14T12:53:46.888392524Z","message":{"..."},"done":true,"done_reason":"stop","total_duration":15905907345,"prompt_eval_count":432,"eval_count":775}

echo "{\"model\": \"qwen3.5:397b-cloud\", \"messages\": [{\"role\": \"user\",  \"content\": \"\",\"images\": [\"$IMG\"] }],\"stream\": false, \"format\": \"json\"}" | curl -X POST http://0.0.0.0:11434/api/chat -H "Content-Type: application/json" -H "Authorization: Bearer "$OLLAMA_API_KEY -d @-
{"model":"qwen3.5:397b","created_at":"2026-04-14T21:51:49.78707483Z","message":{"..."},"done":true,"done_reason":"stop","total_duration":15994634694,"prompt_eval_count":432,"eval_count":889}

echo "{\"model\": \"gemma4:31b-it-q4_K_M\", \"messages\": [{\"role\": \"user\",  \"content\": \"\",\"images\": [\"$IMG\"] }],\"stream\": false}" | curl -X POST http://0.0.0.0:11434/api/chat -H "Content-Type: application/json" -H "Authorization: Bearer "$OLLAMA_API_KEY -d @-
{"model":"gemma4:31b-it-q4_K_M","created_at":"2026-04-14T21:56:58.18721552Z","message":{"..."},"done":true,"done_reason":"stop","total_duration":90482110976,"load_duration":285760912,"prompt_eval_count":281,"prompt_eval_duration":99862896,"eval_count":915,"eval_duration":8977992150

echo "{\"model\": \"gemma4:31b-it-q4_K_M\", \"messages\": [{\"role\": \"user\",  \"content\": \"\",\"images\": [\"$IMG\"] }],\"stream\": false, \"format\": \"json\"}" | curl -X POST http://0.0.0.0:11434/api/chat -H "Content-Type: application/json" -H "Authorization: Bearer "$OLLAMA_API_KEY -d @-
{"model":"gemma4:31b-it-q4_K_M","created_at":"2026-04-14T21:59:13.743806688Z","message":{"..."},"done":true,"done_reason":"stop","total_duration":56701847024,"load_duration":220037664,"prompt_eval_count":286,"prompt_eval_duration":116230352,"eval_count":28,"eval_duration":2635753616}

Image

(note; the attached image is a fake bank transfer order with synthetic imaginary data)

Relevant log output

OS

Linux

GPU

NVIDIA GB10 (DGX SPARK)

CPU

No response

Ollama version

0.20.4

Originally created by @fchahun on GitHub (Apr 14, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/15592 ### What is the issue? With local versions of Qwen3.5 (9b, 27b, 35b, 122b), using a blank prompt and a single image (attached) as input, I notice a huge difference in input tokens depending whether format is unspecified or assigned to "json" (_prompt_eval_count_ increases from 432 to 1789). This does not occur with the cloud version (397b-cloud) (_prompt_eval_count_ remains unchanged at 432) This does not occur either with other models such as gemma4 (_prompt_eval_count_ slightly increases from 281 to 286) This phenomenon can be easily reproduced using the attached image an the **curl** commands below. What is the reason for that? ``` IMG=$(base64 < Image_001.jpeg | tr -d '\n') echo "{\"model\": \"qwen3.5:27b\", \"messages\": [{\"role\": \"user\", \"content\": \"\",\"images\": [\"$IMG\"] }],\"stream\": false}" | curl -X POST http://0.0.0.0:11434/api/chat -H "Content-Type: application/json" -d @- {"model":"qwen3.5:27b","created_at":"2026-04-14T12:57:14.954993416Z","message":{"..."},"done":true,"done_reason":"stop","total_duration":160473406601,"load_duration":6219169752,"prompt_eval_count":432,"prompt_eval_duration":724455268,"eval_count":2003,"eval_duration":152220636272} echo "{\"model\": \"qwen3.5:27b-q4_K_M\", \"messages\": [{\"role\": \"user\", \"content\": \"\",\"images\": [\"$IMG\"] }],\"stream\": false, \"format\": \"json\"}" | curl -X POST http://0.0.0.0:11434/api/chat -H "Content-Type: application/json" -d @- {"model":"qwen3.5:27b-q4_K_M","created_at":"2026-04-14T21:27:56.795489648Z","message":{"..."},"done":true,"done_reason":"stop","total_duration":156916654288,"load_duration":8222672080,"prompt_eval_count":1789,"prompt_eval_duration":2405578208,"eval_count":300,"eval_duration":26354827648} echo "{\"model\": \"qwen3.5:397b-cloud\", \"messages\": [{\"role\": \"user\", \"content\": \"\",\"images\": [\"$IMG\"] }],\"stream\": false}" | curl -X POST http://0.0.0.0:11434/api/chat -H "Content-Type: application/json" -H "Authorization: Bearer $OLLAMA_API_KEY" -d @- {"model":"qwen3.5:397b","created_at":"2026-04-14T12:53:46.888392524Z","message":{"..."},"done":true,"done_reason":"stop","total_duration":15905907345,"prompt_eval_count":432,"eval_count":775} echo "{\"model\": \"qwen3.5:397b-cloud\", \"messages\": [{\"role\": \"user\", \"content\": \"\",\"images\": [\"$IMG\"] }],\"stream\": false, \"format\": \"json\"}" | curl -X POST http://0.0.0.0:11434/api/chat -H "Content-Type: application/json" -H "Authorization: Bearer "$OLLAMA_API_KEY -d @- {"model":"qwen3.5:397b","created_at":"2026-04-14T21:51:49.78707483Z","message":{"..."},"done":true,"done_reason":"stop","total_duration":15994634694,"prompt_eval_count":432,"eval_count":889} echo "{\"model\": \"gemma4:31b-it-q4_K_M\", \"messages\": [{\"role\": \"user\", \"content\": \"\",\"images\": [\"$IMG\"] }],\"stream\": false}" | curl -X POST http://0.0.0.0:11434/api/chat -H "Content-Type: application/json" -H "Authorization: Bearer "$OLLAMA_API_KEY -d @- {"model":"gemma4:31b-it-q4_K_M","created_at":"2026-04-14T21:56:58.18721552Z","message":{"..."},"done":true,"done_reason":"stop","total_duration":90482110976,"load_duration":285760912,"prompt_eval_count":281,"prompt_eval_duration":99862896,"eval_count":915,"eval_duration":8977992150 echo "{\"model\": \"gemma4:31b-it-q4_K_M\", \"messages\": [{\"role\": \"user\", \"content\": \"\",\"images\": [\"$IMG\"] }],\"stream\": false, \"format\": \"json\"}" | curl -X POST http://0.0.0.0:11434/api/chat -H "Content-Type: application/json" -H "Authorization: Bearer "$OLLAMA_API_KEY -d @- {"model":"gemma4:31b-it-q4_K_M","created_at":"2026-04-14T21:59:13.743806688Z","message":{"..."},"done":true,"done_reason":"stop","total_duration":56701847024,"load_duration":220037664,"prompt_eval_count":286,"prompt_eval_duration":116230352,"eval_count":28,"eval_duration":2635753616} ``` ![Image](https://github.com/user-attachments/assets/8f815b67-0d4d-41b6-8d72-f87259e6b0e9) (note; the attached image is a fake bank transfer order with synthetic imaginary data) ### Relevant log output ```shell ``` ### OS Linux ### GPU NVIDIA GB10 (DGX SPARK) ### CPU _No response_ ### Ollama version 0.20.4
GiteaMirror added the bug label 2026-05-05 03:18:26 -05:00
GiteaMirror commented 2026-05-05 03:18:31 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Apr 15, 2026):

https://github.com/ollama/ollama/issues/14957

<!-- gh-comment-id:4248372664 --> @rick-github commented on GitHub (Apr 15, 2026): https://github.com/ollama/ollama/issues/14957
GiteaMirror commented 2026-05-05 03:18:34 -05:00
Author
Owner
Copy Link

@fchahun commented on GitHub (Apr 15, 2026):

Thank you. This also explains why the prompt_eval_count varies with different images all exactly the same dimensions.

But why is the situation différent for the cloud version (qwen3.5:397b-cloud)? Does it use a different inference framework?

<!-- gh-comment-id:4249836677 --> @fchahun commented on GitHub (Apr 15, 2026): Thank you. This also explains why the prompt_eval_count varies with different images all exactly the same dimensions. But why is the situation différent for the cloud version (qwen3.5:397b-cloud)? Does it use a different inference framework?
GiteaMirror commented 2026-05-05 03:18:37 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Apr 15, 2026):

Yes, different inference framework and cloud doesn't currently support structured outputs.

<!-- gh-comment-id:4251169059 --> @rick-github commented on GitHub (Apr 15, 2026): Yes, different inference framework and cloud [doesn't currently support](https://github.com/ollama/ollama/issues/12362) structured outputs.
GiteaMirror commented 2026-05-05 03:18:38 -05:00
Author
Owner
Copy Link

@PureBlissAK commented on GitHub (Apr 18, 2026):

🤖 Automated Triage & Analysis Report

Issue: #15592
Analyzed: 2026-04-18T18:19:27.003914

Analysis

  • Type: unknown
  • Severity: medium
  • Components: unknown

Implementation Plan

  • Effort: medium
  • Steps:

This issue has been triaged and marked for implementation.

<!-- gh-comment-id:4274304890 --> @PureBlissAK commented on GitHub (Apr 18, 2026): <!-- ollama-issue-orchestrator:v1 issue:15592 --> ## 🤖 Automated Triage & Analysis Report **Issue**: #15592 **Analyzed**: 2026-04-18T18:19:27.003914 ### Analysis - **Type**: unknown - **Severity**: medium - **Components**: unknown ### Implementation Plan - **Effort**: medium - **Steps**: *This issue has been triaged and marked for implementation.*
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#72010
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?