Issue Station
Sign In
Tools hereToolbox

ollama - 💡(How to fix) Fix Registering fine-tuned models

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…
RAW_BUFFERClick to expand / collapse

What is the issue?

I've been trying to fine tune qwen3.5:122b and then register it as ollama model locally to run inference. First of all I couldn't find which model is actually being used, I assumed the one available in huggingace, is that true? Second of all, I tried converting it to 4_Q_K format like the model available natively using llama.cpp and there is a weird delta in size - my fine-tuned model weighs 74GB while the original model weighs 81GB. Can you please share some instructions to fine tune a model identical to what's available? This is crucial for research purposes.

Thank you!

Relevant log output

OS

No response

GPU

No response

CPU

No response

Ollama version

No response

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…
#model download#tokenizer error#prompt formatting#chain error#conversation history

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 Registering fine-tuned models