github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #369] Crash when running with metal #164

New Issue
Closed
opened 2026-04-12 09:41:56 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-12 09:41:56 -05:00
Owner
Copy Link

Originally created by @jmorganca on GitHub (Aug 17, 2023).
Original GitHub issue: https://github.com/ollama/ollama/issues/369

ggml_metal_init: recommendedMaxWorkingSetSize = 10922.67 MB
ggml_metal_init: hasUnifiedMemory             = true
ggml_metal_init: maxTransferRate              = built-in GPU
llama_new_context_with_model: max tensor size =   132.81 MB
ggml_metal_add_buffer: allocated 'data            ' buffer, size =  6829.08 MB, ( 6831.52 / 10922.67)
ggml_metal_add_buffer: allocated 'eval            ' buffer, size =    10.17 MB, ( 6841.69 / 10922.67)
ggml_metal_add_buffer: allocated 'kv              ' buffer, size =  1026.00 MB, ( 7867.69 / 10922.67)
ggml_metal_add_buffer: allocated 'scr0            ' buffer, size =   228.00 MB, ( 8095.69 / 10922.67)
ggml_metal_add_buffer: allocated 'scr1            ' buffer, size =   160.00 MB, ( 8255.69 / 10922.67)
GGML_ASSERT: ggml-metal.m:933: false && "not implemented"
Asserting on type 8
GGML_ASSERT: ggml-metal.m:874: false && "not implemented"
Originally created by @jmorganca on GitHub (Aug 17, 2023). Original GitHub issue: https://github.com/ollama/ollama/issues/369 ``` ggml_metal_init: recommendedMaxWorkingSetSize = 10922.67 MB ggml_metal_init: hasUnifiedMemory = true ggml_metal_init: maxTransferRate = built-in GPU llama_new_context_with_model: max tensor size = 132.81 MB ggml_metal_add_buffer: allocated 'data ' buffer, size = 6829.08 MB, ( 6831.52 / 10922.67) ggml_metal_add_buffer: allocated 'eval ' buffer, size = 10.17 MB, ( 6841.69 / 10922.67) ggml_metal_add_buffer: allocated 'kv ' buffer, size = 1026.00 MB, ( 7867.69 / 10922.67) ggml_metal_add_buffer: allocated 'scr0 ' buffer, size = 228.00 MB, ( 8095.69 / 10922.67) ggml_metal_add_buffer: allocated 'scr1 ' buffer, size = 160.00 MB, ( 8255.69 / 10922.67) GGML_ASSERT: ggml-metal.m:933: false && "not implemented" Asserting on type 8 GGML_ASSERT: ggml-metal.m:874: false && "not implemented" ```
GiteaMirror added the bug label 2026-04-12 09:41:56 -05:00
GiteaMirror commented 2026-04-12 09:41:57 -05:00
Author
Owner
Copy Link

@mxyng commented on GitHub (Aug 17, 2023):

This is very likely due to using a quantization (q5_0, q5_1, q8_0) that doesn't support metal. Non-quantized models will also produce this error. The next release should fix this by disabling metal dynamically when loading an unsupported model

<!-- gh-comment-id:1681655954 --> @mxyng commented on GitHub (Aug 17, 2023): This is very likely due to using a quantization (q5_0, q5_1, q8_0) that doesn't support metal. Non-quantized models will also produce this error. The next release should fix this by disabling metal dynamically when loading an unsupported model
GiteaMirror commented 2026-04-12 09:41:57 -05:00
Author
Owner
Copy Link

@mchiang0610 commented on GitHub (Aug 22, 2023):

Haven't been able to reproduce this one. Closing for now. Can repo later if needed

<!-- gh-comment-id:1687260134 --> @mchiang0610 commented on GitHub (Aug 22, 2023): Haven't been able to reproduce this one. Closing for now. Can repo later if needed
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#164
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?