github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 08:30:05 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #8564] Error: server metal not listed in available servers map #5530

New Issue
Closed
opened 2026-04-12 16:46:46 -05:00 by GiteaMirror · 5 comments
GiteaMirror commented 2026-04-12 16:46:46 -05:00
Owner
Copy Link

Originally created by @felix021 on GitHub (Jan 24, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/8564

What is the issue?

I downloaded Ollama today on my Macbook (Apple M3 Pro, with MacOS Sonoma 14.3 23D56), and tried to run deepseek-r1:8b, but ollama failed with this error:

$ ollama run deepseek-r1:8b
Error: [0] server metal not listed in available servers map[]

p.s. I can run this model with llama-cli on the same device.

OS

macOS

GPU

Apple

CPU

Apple

Ollama version

0.5.7

Originally created by @felix021 on GitHub (Jan 24, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/8564 ### What is the issue? I downloaded Ollama today on my Macbook (Apple M3 Pro, with MacOS Sonoma 14.3 23D56), and tried to run deepseek-r1:8b, but ollama failed with this error: > $ ollama run deepseek-r1:8b > Error: [0] server metal not listed in available servers map[] p.s. I can run this model with llama-cli on the same device. ### OS macOS ### GPU Apple ### CPU Apple ### Ollama version 0.5.7
GiteaMirror added the bug label 2026-04-12 16:46:46 -05:00
GiteaMirror commented 2026-04-12 16:46:48 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jan 24, 2025):

This error is annotated with // Shouldn't happen in the source code. What's in the server logs?

<!-- gh-comment-id:2612726225 --> @rick-github commented on GitHub (Jan 24, 2025): This error is annotated with `// Shouldn't happen` in the source code. What's in the [server logs](https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md#how-to-troubleshoot-issues)?
GiteaMirror commented 2026-04-12 16:46:49 -05:00
Author
Owner
Copy Link

@felix021 commented on GitHub (Jan 26, 2025):

This error is annotated with // Shouldn't happen in the source code. What's in the server logs?

Found in .ollama/logs:

time=2025-01-26T10:24:35.514+08:00 level=INFO source=sched.go:714 msg="new model will fit in available VRAM in single GPU, loading" model=/Users/user/.ollama/models/blobs/sha256-6340dc3229b0d08ea9cc49b75d4098702983e17b4c096d57afbbf2ffc813f2be gpu=0 parallel=4 available=28991029248 required="6.5 GiB"
time=2025-01-26T10:24:35.514+08:00 level=INFO source=server.go:104 msg="system memory" total="36.0 GiB" free="12.5 GiB" free_swap="0 B"
time=2025-01-26T10:24:35.515+08:00 level=INFO source=memory.go:356 msg="offload to metal" layers.requested=-1 layers.model=33 layers.offload=33 layers.split="" memory.available="[27.0 GiB]" memory.gpu_overhead="0 B" memory.required.full="6.5 GiB" memory.required.partial="6.5 GiB" memory.required.kv="1.0 GiB" memory.required.allocations="[6.5 GiB]" memory.weights.total="4.9 GiB" memory.weights.repeating="4.5 GiB" memory.weights.nonrepeating="411.0 MiB" memory.graph.full="560.0 MiB" memory.graph.partial="560.0 MiB"
time=2025-01-26T10:24:35.515+08:00 level=ERROR source=server.go:279 msg="server list inconsistent" error="[0] server metal not listed in available servers map[]"
time=2025-01-26T10:24:35.515+08:00 level=ERROR source=server.go:429 msg="unable to load any llama server" error="[0] server metal not listed in available servers map[]"
time=2025-01-26T10:24:35.515+08:00 level=INFO source=sched.go:428 msg="NewLlamaServer failed" model=/Users/user/.ollama/models/blobs/sha256-6340dc3229b0d08ea9cc49b75d4098702983e17b4c096d57afbbf2ffc813f2be error="[0] server metal not listed in available servers map[]"

<!-- gh-comment-id:2614179053 --> @felix021 commented on GitHub (Jan 26, 2025): > This error is annotated with `// Shouldn't happen` in the source code. What's in the [server logs](https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md#how-to-troubleshoot-issues)? Found in `.ollama/logs`: > time=2025-01-26T10:24:35.514+08:00 level=INFO source=sched.go:714 msg="new model will fit in available VRAM in single GPU, loading" model=/Users/user/.ollama/models/blobs/sha256-6340dc3229b0d08ea9cc49b75d4098702983e17b4c096d57afbbf2ffc813f2be gpu=0 parallel=4 available=28991029248 required="6.5 GiB" > time=2025-01-26T10:24:35.514+08:00 level=INFO source=server.go:104 msg="system memory" total="36.0 GiB" free="12.5 GiB" free_swap="0 B" > time=2025-01-26T10:24:35.515+08:00 level=INFO source=memory.go:356 msg="offload to metal" layers.requested=-1 layers.model=33 layers.offload=33 layers.split="" memory.available="[27.0 GiB]" memory.gpu_overhead="0 B" memory.required.full="6.5 GiB" memory.required.partial="6.5 GiB" memory.required.kv="1.0 GiB" memory.required.allocations="[6.5 GiB]" memory.weights.total="4.9 GiB" memory.weights.repeating="4.5 GiB" memory.weights.nonrepeating="411.0 MiB" memory.graph.full="560.0 MiB" memory.graph.partial="560.0 MiB" > time=2025-01-26T10:24:35.515+08:00 level=ERROR source=server.go:279 msg="server list inconsistent" error="[0] server metal not listed in available servers map[]" > time=2025-01-26T10:24:35.515+08:00 level=ERROR source=server.go:429 msg="unable to load any llama server" error="[0] server metal not listed in available servers map[]" > time=2025-01-26T10:24:35.515+08:00 level=INFO source=sched.go:428 msg="NewLlamaServer failed" model=/Users/user/.ollama/models/blobs/sha256-6340dc3229b0d08ea9cc49b75d4098702983e17b4c096d57afbbf2ffc813f2be error="[0] server metal not listed in available servers map[]"
GiteaMirror commented 2026-04-12 16:46:50 -05:00
Author
Owner
Copy Link

@glud123 commented on GitHub (Feb 2, 2025):

You can try the following steps:

  1. Exit ollama.
  2. Run the ollama service as an administrator with sudo ollama serve.
  3. After successfully starting the ollama service, run the required model ollama run deepseek-r1:8b.
<!-- gh-comment-id:2629211718 --> @glud123 commented on GitHub (Feb 2, 2025): You can try the following steps: 1. Exit ollama. 2. Run the ollama service as an administrator with `sudo ollama serve`. 3. After successfully starting the ollama service, run the required model `ollama run deepseek-r1:8b`.
GiteaMirror commented 2026-04-12 16:46:51 -05:00
Author
Owner
Copy Link

@felix021 commented on GitHub (Feb 5, 2025):

You can try the following steps:

  1. Exit ollama.
  2. Run the ollama service as an administrator with sudo ollama serve.
  3. After successfully starting the ollama service, run the required model ollama run deepseek-r1:8b.

Cool, that worked, thx!

<!-- gh-comment-id:2636470178 --> @felix021 commented on GitHub (Feb 5, 2025): > You can try the following steps: > > 1. Exit ollama. > 2. Run the ollama service as an administrator with `sudo ollama serve`. > 3. After successfully starting the ollama service, run the required model `ollama run deepseek-r1:8b`. Cool, that worked, thx!
GiteaMirror commented 2026-04-12 16:46:52 -05:00
Author
Owner
Copy Link

@felix021 commented on GitHub (Feb 5, 2025):

Btw, would you please add that to the error message?

<!-- gh-comment-id:2636471167 --> @felix021 commented on GitHub (Feb 5, 2025): Btw, would you please add that to the error message?
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#5530
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?