Issue Station
Sign In
Tools hereToolbox

ollama - 💡(How to fix) Fix About v0.20.0 pre-release [2 comments, 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#15227•Fetched 2026-04-08 02:34:09
View on GitHub
Comments
2
Participants
1
Timeline
5
Reactions
0
Author
methaqualonmethaqualon
Participants
methaqualonmethaqualon
Timeline (top)
commented ×2closed ×1labeled ×1subscribed ×1

Error Message

root@ollama:~# ollama run gemma4:e4b-it-q8_0 Error: 500 Internal Server Error: llama runner process has terminated: %!w(<nil>)

Code Example

root@ollama:~# ollama run gemma4:e4b-it-q8_0
Error: 500 Internal Server Error: llama runner process has terminated: %!w(<nil>)

---

root@ollama:~# ollama run gemma4:e4b-it-q8_0
Error: 500 Internal Server Error: llama runner process has terminated: %!w(<nil>)
root@ollama:~# journalctl -u ollama -f
апр 02 17:25:11 ollama ollama[577]: time=2026-04-02T17:25:11.416Z level=INFO source=server.go:1386 msg="waiting for server to become available" status="llm server loading model"
апр 02 17:25:11 ollama ollama[577]: panic: failed to load model: unassigned tensor: model.audio_tower.layers.10.feed_forward1.ffw_layer_1.output_max
апр 02 17:25:11 ollama ollama[577]: goroutine 83 [running]:
апр 02 17:25:11 ollama ollama[577]: github.com/ollama/ollama/runner/ollamarunner.(*Server).loadModel(0xc0005e43c0)
апр 02 17:25:11 ollama ollama[577]:         github.com/ollama/ollama/runner/ollamarunner/runner.go:1258 +0x1d4
апр 02 17:25:11 ollama ollama[577]: created by github.com/ollama/ollama/runner/ollamarunner.(*Server).load in goroutine 10
апр 02 17:25:11 ollama ollama[577]:         github.com/ollama/ollama/runner/ollamarunner/runner.go:1347 +0x625
апр 02 17:25:11 ollama ollama[577]: time=2026-04-02T17:25:11.998Z level=INFO source=server.go:1386 msg="waiting for server to become available" status="llm server not responding"
апр 02 17:25:12 ollama ollama[577]: time=2026-04-02T17:25:12.249Z level=ERROR source=sched.go:567 msg="error loading llama server" error="llama runner process has terminated: %!w(<nil>)"
апр 02 17:25:12 ollama ollama[577]: [GIN] 2026/04/02 - 17:25:12 | 500 |  1.607744997s |       127.0.0.1 | POST     "/api/generate"
RAW_BUFFERClick to expand / collapse

What is the issue?

root@ollama:~# ollama run gemma4:e4b-it-q8_0
Error: 500 Internal Server Error: llama runner process has terminated: %!w(<nil>)

but gemma4:26b-a4b-it-q4_K_M works perfectly. May be some problem in audio things.

ask for any further info if needed

Relevant log output

root@ollama:~# ollama run gemma4:e4b-it-q8_0
Error: 500 Internal Server Error: llama runner process has terminated: %!w(<nil>)
root@ollama:~# journalctl -u ollama -f
апр 02 17:25:11 ollama ollama[577]: time=2026-04-02T17:25:11.416Z level=INFO source=server.go:1386 msg="waiting for server to become available" status="llm server loading model"
апр 02 17:25:11 ollama ollama[577]: panic: failed to load model: unassigned tensor: model.audio_tower.layers.10.feed_forward1.ffw_layer_1.output_max
апр 02 17:25:11 ollama ollama[577]: goroutine 83 [running]:
апр 02 17:25:11 ollama ollama[577]: github.com/ollama/ollama/runner/ollamarunner.(*Server).loadModel(0xc0005e43c0)
апр 02 17:25:11 ollama ollama[577]:         github.com/ollama/ollama/runner/ollamarunner/runner.go:1258 +0x1d4
апр 02 17:25:11 ollama ollama[577]: created by github.com/ollama/ollama/runner/ollamarunner.(*Server).load in goroutine 10
апр 02 17:25:11 ollama ollama[577]:         github.com/ollama/ollama/runner/ollamarunner/runner.go:1347 +0x625
апр 02 17:25:11 ollama ollama[577]: time=2026-04-02T17:25:11.998Z level=INFO source=server.go:1386 msg="waiting for server to become available" status="llm server not responding"
апр 02 17:25:12 ollama ollama[577]: time=2026-04-02T17:25:12.249Z level=ERROR source=sched.go:567 msg="error loading llama server" error="llama runner process has terminated: %!w(<nil>)"
апр 02 17:25:12 ollama ollama[577]: [GIN] 2026/04/02 - 17:25:12 | 500 |  1.607744997s |       127.0.0.1 | POST     "/api/generate"

OS

Linux

GPU

Intel

CPU

Intel

Ollama version

0.20.0-rc0

extent analysis

TL;DR

The issue is likely caused by a problem with loading the audio model in the gemma4:e4b-it-q8_0 configuration, and a workaround may involve checking the model configuration or updating the Ollama version.

Guidance

  • Check the model configuration for gemma4:e4b-it-q8_0 to ensure that the audio tower is properly defined and loaded.
  • Verify that the model.audio_tower.layers.10.feed_forward1.ffw_layer_1.output_max tensor is assigned and loaded correctly.
  • Consider updating the Ollama version to a newer release, as the current version 0.20.0-rc0 may contain bugs or issues that are fixed in later versions.
  • Review the log output to ensure that there are no other errors or warnings that may be related to the issue.

Notes

The issue seems to be specific to the gemma4:e4b-it-q8_0 configuration, as the gemma4:26b-a4b-it-q4_K_M configuration works perfectly. This suggests that the problem may be related to the model configuration or the audio tower.

Recommendation

Apply workaround: Check the model configuration and update the Ollama version if necessary, as the current version may contain bugs or issues that are fixed in later versions.

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#cache issue#memory leak#API versioning#request timeout

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 About v0.20.0 pre-release [2 comments, 1 participants]