Issue Station
Sign In
Tools hereToolbox

ollama - 💡(How to fix) Fix importing safetensors model zsh: killed [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#15800•Fetched 2026-04-25 06:03:27
View on GitHub
Comments
0
Participants
1
Timeline
1
Reactions
0
Author
eduard-sukhareveduard-sukharev
Participants
eduard-sukhareveduard-sukharev
Timeline (top)
labeled ×1

Error Message

Is it running out of memory or is there some internal error?

Code Example

FROM /Volumes/EXT_SSD/mlx-community_gemma-4-e4b-4bit

TEMPLATE {{ .Prompt }}
RENDERER gemma4
PARSER gemma4
PARAMETER top_p 0.95
PARAMETER temperature 1
PARAMETER top_k 64
LICENSE """                                Apache License

---

GOMAXPROCS=1 ollama create gemma4:e4b-4bit -f gemma4_e4b_4bit.Modelfile --experimental

---

importing safetensors model ⠧ zsh: killed     GOMAXPROCS=1 ollama create gemma4:e4b-4bit -f gemma4_e4b_4bit.Modelfile --experimental

---
RAW_BUFFERClick to expand / collapse

What is the issue?

I'm trying to build a model with Modelfile from mlx-community/gemma-4-e4b-4bit quantized mlx model. I have pulled the model files with hf download, the Modelfile is basically the same as ollama's gemma4:e2b:

FROM /Volumes/EXT_SSD/mlx-community_gemma-4-e4b-4bit

TEMPLATE {{ .Prompt }}
RENDERER gemma4
PARSER gemma4
PARAMETER top_p 0.95
PARAMETER temperature 1
PARAMETER top_k 64
LICENSE """                                Apache License

I'm doing this to try to fit the e4b model onto a 8Gb Mac Mini, which I actually run creating on:

GOMAXPROCS=1 ollama create gemma4:e4b-4bit -f gemma4_e4b_4bit.Modelfile --experimental

and after a couple of seconds thinking it just quits:

importing safetensors model ⠧ zsh: killed     GOMAXPROCS=1 ollama create gemma4:e4b-4bit -f gemma4_e4b_4bit.Modelfile --experimental

Is it running out of memory or is there some internal error?

Relevant log output

OS

macOS

GPU

Apple

CPU

Apple

Ollama version

0.21.2

extent analysis

TL;DR

The issue is likely due to the model not fitting in memory, and a workaround could be to adjust the model parameters or use a machine with more memory.

Guidance

  • The error message "zsh: killed" suggests that the process was terminated, possibly due to running out of memory.
  • Try reducing the model size or complexity by adjusting parameters such as top_p, temperature, or top_k in the Modelfile.
  • Verify if the issue is memory-related by monitoring the system's memory usage while running the command.
  • Consider using a machine with more than 8Gb of memory to run the model.

Example

No code snippet is provided as it is not clearly supported by the issue.

Notes

The issue lacks detailed log output, which could provide more insight into the problem. Additionally, the experimental flag used with the ollama create command may introduce uncertainties.

Recommendation

Apply workaround: Adjust model parameters or use a machine with more memory, as the current setup seems to be running out of memory.

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…
#api#installation#tensor shape#autograd error#model save/load

Still need to ship something?

×6

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

Back to top recommendations

TRENDING