Issue Station
Sign In
Tools hereToolbox

ollama - 💡(How to fix) Fix Ollama create does not import the full modelfile, ignoring RENDERER, PARSER, PARAMETER [1 participants]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…
GitHub stats
ollama/ollama#15810•Fetched 2026-04-26 05:06:07
View on GitHub
Comments
0
Participants
1
Timeline
1
Reactions
0
Author
chigkimchigkim
Participants
chigkimchigkim
Timeline (top)
labeled ×1

Error Message

As a result, if I try to use the finetuned model, it throws an error saying it does not support tools.

Code Example

FROM .
TEMPLATE {{ .Prompt }}
RENDERER qwen3.5
PARSER qwen3.5
PARAMETER min_p 0
PARAMETER presence_penalty 1.5
PARAMETER repeat_penalty 1
PARAMETER temperature 1
PARAMETER top_k 20
PARAMETER top_p 0.95
LICENSE """
...
"""

---

FROM /Users/cgk/.ollama/models/blobs/sha256-522d319f1b8e18cf7f134780e5dcce08685653934b4e2737974dba707191bcb7
TEMPLATE {{ .Prompt }}

---
RAW_BUFFERClick to expand / collapse

What is the issue?

First I saved a modelfile with ollama show qwen3.6:35b-a3b-q8_0 --modelfile>qwen36.modelfile. Then I pointed the modelfile to a finetuned model in safetensor, so qwen36.modelfile looks like this:

FROM .
TEMPLATE {{ .Prompt }}
RENDERER qwen3.5
PARSER qwen3.5
PARAMETER min_p 0
PARAMETER presence_penalty 1.5
PARAMETER repeat_penalty 1
PARAMETER temperature 1
PARAMETER top_k 20
PARAMETER top_p 0.95
LICENSE """
...
"""

Then I imported the finetuned model with -f qwen36.modelfile. However, if I run ollama show finetuned --modelfile, the imported modelfile only shows the following:

FROM /Users/cgk/.ollama/models/blobs/sha256-522d319f1b8e18cf7f134780e5dcce08685653934b4e2737974dba707191bcb7
TEMPLATE {{ .Prompt }}

A lot of things are missing like: RENDERER qwen3.5 PARSER qwen3.5

As a result, if I try to use the finetuned model, it throws an error saying it does not support tools.

Relevant log output

OS

macOS

GPU

Apple

CPU

Apple

Ollama version

0.21.2

extent analysis

TL;DR

The issue can be resolved by ensuring that the modelfile import process correctly preserves all parameters from the original modelfile.

Guidance

  • Verify that the ollama command used to import the finetuned model supports preserving all parameters from the original modelfile.
  • Check the documentation for the -f flag to see if there are any additional options or flags required to preserve the RENDERER, PARSER, and other parameters.
  • Compare the original modelfile (qwen36.modelfile) with the imported modelfile to identify any other missing parameters or settings.
  • Consider manually editing the imported modelfile to add the missing parameters, such as RENDERER and PARSER, to see if this resolves the issue.

Example

No code snippet is provided as the issue is related to the ollama command and modelfile import process.

Notes

The issue may be specific to the ollama version (0.21.2) or the macOS environment, and further investigation may be required to determine the root cause.

Recommendation

Apply a workaround by manually editing the imported modelfile to add the missing parameters, as this may provide a temporary solution until the underlying issue is resolved.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…
#dependency conflict#environment setup#docker error#permission error#memory optimization

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING

ollama - 💡(How to fix) Fix Ollama create does not import the full modelfile, ignoring RENDERER, PARSER, PARAMETER [1 participants]