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 #1248] v0.1.11 Crashes on Intel Mac #637

New Issue
Closed
opened 2026-04-12 10:20:10 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-12 10:20:10 -05:00
Owner
Copy Link

Originally created by @10REMSSeiller on GitHub (Nov 22, 2023).
Original GitHub issue: https://github.com/ollama/ollama/issues/1248

Originally assigned to: @jmorganca on GitHub.

v0.1.9 ran successfully on my Mac, but v0.1.11 causes crash. I'm not sure why. Below is excerpt of crash log.
I was able to revert and run v0.1.9.
For verification, I trashed the original ~/.ollama and application support folders and reinstalled v0.1.11. Same results. What other info is needed?

Process: ollama-runner [1470]
Path: /private/var/folders/*/ollama-runner
Version: ???
Code Type: X86-64 (Native)
Parent Process: ollama [697]
Time Awake Since Boot: 960 seconds
System Integrity Protection: enabled
Crashed Thread: 0 Dispatch queue: com.apple.main-thread
Exception Type: EXC_BAD_INSTRUCTION (SIGILL)
Exception Codes: 0x0000000000000001, 0x0000000000000000
Exception Note: EXC_CORPSE_NOTIFY
Termination Reason: Namespace SIGNAL, Code 4 Illegal instruction: 4
Terminating Process: exc handler [1470]

Thread 0 Crashed:: Dispatch queue: com.apple.main-thread
0 ollama-runner 0x105fc05e8 nlohmann::json_abi_v3_11_2::basic_json<nlohmann::json_abi_v3_11_2::ordered_map, std::__1::vector, std::__1::basic_string<char, std::__1::char_traits, std::__1::allocator >, bool, long long, unsigned long long, double, std::__1::allocator, nlohmann::json_abi_v3_11_2::adl_serializer, std::__1::vector<unsigned char, std::__1::allocator > >::dump(int, char, bool, nlohmann::json_abi_v3_11_2::detail::error_handler_t) const + 424
1 ollama-runner 0x105fbc2ba server_log(char const*, char const*, int, char const*, nlohmann::json_abi_v3_11_2::basic_json<nlohmann::json_abi_v3_11_2::ordered_map, std::__1::vector, std::__1::basic_string<char, std::__1::char_traits, std::__1::allocator >, bool, long long, unsigned long long, double, std::__1::allocator, nlohmann::json_abi_v3_11_2::adl_serializer, std::__1::vector<unsigned char, std::__1::allocator > > const&) + 1114
2 ollama-runner 0x105fb952d main + 6349
3 dyld 0x10c79d52e start + 462

Below is the fresh server.log

2023/11/22 13:44:28 images.go:779: total blobs: 0
2023/11/22 13:44:28 images.go:786: total unused blobs removed: 0
2023/11/22 13:44:28 routes.go:777: Listening on 127.0.0.1:11434 (version 0.1.11)
[GIN] 2023/11/22 - 13:48:13 | 200 | 1.315832ms | 127.0.0.1 | HEAD "/"
[GIN] 2023/11/22 - 13:48:13 | 404 | 5.195104ms | 127.0.0.1 | POST "/api/show"
2023/11/22 13:48:16 download.go:123: downloading 22f7f8ef5f4c in 39 100 MB part(s)
2023/11/22 13:55:53 download.go:162: 22f7f8ef5f4c part 16 attempt 0 failed: unexpected EOF, retrying in 1s
2023/11/22 13:59:09 download.go:123: downloading 8c17c2ebb0ea in 1 7.0 KB part(s)
2023/11/22 13:59:12 download.go:123: downloading 7c23fb36d801 in 1 4.8 KB part(s)
2023/11/22 13:59:15 download.go:123: downloading 2e0493f67d0c in 1 59 B part(s)
2023/11/22 13:59:17 download.go:123: downloading 2759286baa87 in 1 105 B part(s)
2023/11/22 13:59:20 download.go:123: downloading 5407e3188df9 in 1 529 B part(s)
[GIN] 2023/11/22 - 13:59:41 | 200 | 11m27s | 127.0.0.1 | POST "/api/pull"
2023/11/22 13:59:41 llama.go:420: starting llama runner
2023/11/22 13:59:41 llama.go:478: waiting for llama runner to start responding
2023/11/22 13:59:41 llama.go:435: signal: illegal instruction
2023/11/22 13:59:41 llama.go:443: error starting llama runner: llama runner process has terminated
2023/11/22 13:59:41 llama.go:509: llama runner stopped successfully
[GIN] 2023/11/22 - 13:59:41 | 500 | 428.633985ms | 127.0.0.1 | POST "/api/generate"

I have a [trashcan] Mac Pro (2013) 6-Core Intel Xeon E5 3.5 GHz running macOS 12.7.1 with AMD FirePro D500 3GB VRAM per PCIe slot, gMux Version: 4.0.11 [3.2.8], and Metal Family: Supported, Metal GPUFamily macOS 2.
I upgraded 16GB RAM to 64GB. llama2 will run, but at 3.92 tokens/s.
I was getting 'not enough available memory' error with dolphin2.2-mistral.

Originally created by @10REMSSeiller on GitHub (Nov 22, 2023). Original GitHub issue: https://github.com/ollama/ollama/issues/1248 Originally assigned to: @jmorganca on GitHub. v0.1.9 ran successfully on my Mac, but v0.1.11 causes crash. I'm not sure why. Below is excerpt of crash log. I was able to revert and run v0.1.9. For verification, I trashed the original ~/.ollama and application support folders and reinstalled v0.1.11. Same results. What other info is needed? > Process: ollama-runner [1470] > Path: /private/var/folders/*/ollama-runner > Version: ??? > Code Type: X86-64 (Native) > Parent Process: ollama [697] > Time Awake Since Boot: 960 seconds > System Integrity Protection: enabled > Crashed Thread: 0 Dispatch queue: com.apple.main-thread > Exception Type: EXC_BAD_INSTRUCTION (SIGILL) > Exception Codes: 0x0000000000000001, 0x0000000000000000 > Exception Note: EXC_CORPSE_NOTIFY > Termination Reason: Namespace SIGNAL, Code 4 Illegal instruction: 4 > Terminating Process: exc handler [1470] > > Thread 0 Crashed:: Dispatch queue: com.apple.main-thread > 0 ollama-runner 0x105fc05e8 nlohmann::json_abi_v3_11_2::basic_json<nlohmann::json_abi_v3_11_2::ordered_map, std::__1::vector, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char> >, bool, long long, unsigned long long, double, std::__1::allocator, nlohmann::json_abi_v3_11_2::adl_serializer, std::__1::vector<unsigned char, std::__1::allocator<unsigned char> > >::dump(int, char, bool, nlohmann::json_abi_v3_11_2::detail::error_handler_t) const + 424 > 1 ollama-runner 0x105fbc2ba server_log(char const*, char const*, int, char const*, nlohmann::json_abi_v3_11_2::basic_json<nlohmann::json_abi_v3_11_2::ordered_map, std::__1::vector, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char> >, bool, long long, unsigned long long, double, std::__1::allocator, nlohmann::json_abi_v3_11_2::adl_serializer, std::__1::vector<unsigned char, std::__1::allocator<unsigned char> > > const&) + 1114 > 2 ollama-runner 0x105fb952d main + 6349 > 3 dyld 0x10c79d52e start + 462 Below is the fresh server.log > 2023/11/22 13:44:28 images.go:779: total blobs: 0 > 2023/11/22 13:44:28 images.go:786: total unused blobs removed: 0 > 2023/11/22 13:44:28 routes.go:777: Listening on 127.0.0.1:11434 (version 0.1.11) > [GIN] 2023/11/22 - 13:48:13 | 200 | 1.315832ms | 127.0.0.1 | HEAD "/" > [GIN] 2023/11/22 - 13:48:13 | 404 | 5.195104ms | 127.0.0.1 | POST "/api/show" > 2023/11/22 13:48:16 download.go:123: downloading 22f7f8ef5f4c in 39 100 MB part(s) > 2023/11/22 13:55:53 download.go:162: 22f7f8ef5f4c part 16 attempt 0 failed: unexpected EOF, retrying in 1s > 2023/11/22 13:59:09 download.go:123: downloading 8c17c2ebb0ea in 1 7.0 KB part(s) > 2023/11/22 13:59:12 download.go:123: downloading 7c23fb36d801 in 1 4.8 KB part(s) > 2023/11/22 13:59:15 download.go:123: downloading 2e0493f67d0c in 1 59 B part(s) > 2023/11/22 13:59:17 download.go:123: downloading 2759286baa87 in 1 105 B part(s) > 2023/11/22 13:59:20 download.go:123: downloading 5407e3188df9 in 1 529 B part(s) > [GIN] 2023/11/22 - 13:59:41 | 200 | 11m27s | 127.0.0.1 | POST "/api/pull" > 2023/11/22 13:59:41 llama.go:420: starting llama runner > 2023/11/22 13:59:41 llama.go:478: waiting for llama runner to start responding > 2023/11/22 13:59:41 llama.go:435: signal: illegal instruction > 2023/11/22 13:59:41 llama.go:443: error starting llama runner: llama runner process has terminated > 2023/11/22 13:59:41 llama.go:509: llama runner stopped successfully > [GIN] 2023/11/22 - 13:59:41 | 500 | 428.633985ms | 127.0.0.1 | POST "/api/generate" > I have a [trashcan] Mac Pro (2013) 6-Core Intel Xeon E5 3.5 GHz running macOS 12.7.1 with AMD FirePro D500 3GB VRAM per PCIe slot, gMux Version: 4.0.11 [3.2.8], and Metal Family: Supported, Metal GPUFamily macOS 2. I upgraded 16GB RAM to 64GB. llama2 will run, but at 3.92 tokens/s. I was getting 'not enough available memory' error with dolphin2.2-mistral.
GiteaMirror added the bug label 2026-04-12 10:20:10 -05:00
GiteaMirror commented 2026-04-12 10:20:11 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (Nov 22, 2023):

Hi there! Thanks for creating this issue and sorry Ollama stopped working for you on this hardware. This should be fixed with d77dde126b. A new release should be out in the coming day or so with this change.

<!-- gh-comment-id:1823579899 --> @jmorganca commented on GitHub (Nov 22, 2023): Hi there! Thanks for creating this issue and sorry Ollama stopped working for you on this hardware. This should be fixed with https://github.com/jmorganca/ollama/commit/d77dde126b5fc6e340a9e65f1b9e33316a2c760c. A new release should be out in the coming day or so with this change.
GiteaMirror commented 2026-04-12 10:20:11 -05:00
Author
Owner
Copy Link

@10REMSSeiller commented on GitHub (Nov 23, 2023):

🦙BAM! You are fast! Thank you!
image

<!-- gh-comment-id:1823769476 --> @10REMSSeiller commented on GitHub (Nov 23, 2023): 🦙BAM! You are fast! Thank you! ![image](https://github.com/jmorganca/ollama/assets/20466077/bc653e89-f960-4d59-91ad-7148bea4c25a)
GiteaMirror commented 2026-04-12 10:20:11 -05:00
Author
Owner
Copy Link

@10REMSSeiller commented on GitHub (Nov 27, 2023):

0.1.12 Fixes this issue. Thanks!

<!-- gh-comment-id:1827174754 --> @10REMSSeiller commented on GitHub (Nov 27, 2023): 0.1.12 Fixes this issue. Thanks!
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#637
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?