[GH-ISSUE #15381] I can't run Gemma4:31b #9838

Open
opened 2026-04-12 22:42:10 -05:00 by GiteaMirror · 12 comments
Owner

Originally created by @Jigit-ship-it on GitHub (Apr 7, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/15381

What is the issue?

I've downloaded directly from Ollama website Gemma4:31b.
However, Ollama(0.20.2) cannot run it as below

Image

Relevant log output


OS

No response

GPU

No response

CPU

No response

Ollama version

latest

Originally created by @Jigit-ship-it on GitHub (Apr 7, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/15381 ### What is the issue? I've downloaded directly from Ollama website Gemma4:31b. However, Ollama(0.20.2) cannot run it as below <img width="1106" height="345" alt="Image" src="https://github.com/user-attachments/assets/6bcbd84b-7021-40e4-9169-8124000b8653" /> ### Relevant log output ```shell ``` ### OS _No response_ ### GPU _No response_ ### CPU _No response_ ### Ollama version latest
GiteaMirror added the bug label 2026-04-12 22:42:10 -05:00
Author
Owner

@Hello-World-Traveler commented on GitHub (Apr 7, 2026):

Did you use ollama run gemma4:31b or ollama list

Also you're not running the latest update.

<!-- gh-comment-id:4197201793 --> @Hello-World-Traveler commented on GitHub (Apr 7, 2026): Did you use `ollama run gemma4:31b` or `ollama list` Also you're not running the latest update.
Author
Owner

@Jigit-ship-it commented on GitHub (Apr 7, 2026):

I used both of them

<!-- gh-comment-id:4197474142 --> @Jigit-ship-it commented on GitHub (Apr 7, 2026): I used both of them
Author
Owner

@Hello-World-Traveler commented on GitHub (Apr 7, 2026):

Without the log it will be hard to understand why it's not working. Don't forget to update Olama.

<!-- gh-comment-id:4197521637 --> @Hello-World-Traveler commented on GitHub (Apr 7, 2026): Without the log it will be hard to understand why it's not working. Don't forget to update Olama.
Author
Owner

@khteh commented on GitHub (Apr 7, 2026):

Same experience with me today! It just silent. No response, not working on anything at all. I run it in k8s with ollama 0.20.2. I set OLLAMA_DEBUG="true" in the container but doesn't have anything in kubectl logs output.

<!-- gh-comment-id:4197635442 --> @khteh commented on GitHub (Apr 7, 2026): Same experience with me today! It just silent. No response, not working on anything at all. I run it in k8s with ollama `0.20.2`. I set `OLLAMA_DEBUG="true"` in the container but doesn't have anything in `kubectl logs` output.
Author
Owner

@khteh commented on GitHub (Apr 7, 2026):

Without the log it will be hard to understand why it's not working. Don't forget to update Olama.

Exactly - without any log at all!

<!-- gh-comment-id:4197741092 --> @khteh commented on GitHub (Apr 7, 2026): > Without the log it will be hard to understand why it's not working. Don't forget to update Olama. Exactly - without any log at all!
Author
Owner

@Hello-World-Traveler commented on GitHub (Apr 7, 2026):

@khteh When someone comes along and ask questions or try and troubleshoot an issue with no details, giving the person (me) a thumbs down doesn't help anyone.

<!-- gh-comment-id:4197815506 --> @Hello-World-Traveler commented on GitHub (Apr 7, 2026): @khteh When someone comes along and ask questions or try and troubleshoot an issue with no details, giving the person (me) a thumbs down doesn't help anyone.
Author
Owner

@Bastiendsp commented on GitHub (Apr 7, 2026):

Hi, i've the same problems, but here are some logs for u guys :

I'm on Ollama 0.20.3 running on DGX Spark

Ubuntu DGX OS

Logs :
ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 CUDA devices:
Device 0: NVIDIA GB10, compute capability 12.1, VMM: yes, ID: GPU-a20637ba-815b-7e34-0ad0-6433b297b7cf
load_backend: loaded CUDA backend from /usr/lib/ollama/cuda_v13/libggml-cuda.so
time=2026-04-07T09:31:22.800Z level=INFO source=ggml.go:104 msg=system CPU.0.NEON=1 CPU.0.ARM_FMA=1 CPU.0.LLAMAFILE=1 CPU.1.NEON=1 CPU.1.ARM_FMA=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=750,800,860,870,890,900,1000,1030,1100,1200,1210 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(clang)
time=2026-04-07T09:31:22.804Z level=INFO source=model.go:97 msg="gemma4: token IDs" image=255999 image_end=258882 audio=256000 audio_end=258883
time=2026-04-07T09:31:22.888Z level=INFO source=model.go:138 msg="vision: decode" elapsed=1.294612ms bounds=(0,0)-(2048,2048)
time=2026-04-07T09:31:22.961Z level=INFO source=model.go:145 msg="vision: preprocess" elapsed=73.101916ms size="[768 768]"
time=2026-04-07T09:31:22.961Z level=INFO source=model.go:148 msg="vision: pixelValues" shape="[768 768 3]" dim0=768 dim1=768 dim2=3
time=2026-04-07T09:31:22.961Z level=INFO source=model.go:152 msg="vision: patches" patchesX=48 patchesY=48 total=2304 patchSize=16
time=2026-04-07T09:31:22.962Z level=INFO source=model.go:156 msg="vision: encoded" elapsed=75.160258ms shape="[5376 256]"
/ml/backend/ggml/ggml/src/ggml-cuda/ggml-cuda.cu:560: GGML_ASSERT(pool_size + reserve_size <= CUDA_POOL_VMM_MAX_SIZE) failed
/usr/lib/ollama/libggml-base.so.0(+0x23070)[0xe6c559523070]
/usr/lib/ollama/libggml-base.so.0(ggml_print_backtrace+0x268)[0xe6c55952304c]
/usr/lib/ollama/libggml-base.so.0(ggml_abort+0xe0)[0xe6c559521fe0]
/usr/lib/ollama/cuda_v13/libggml-cuda.so(_ZN18ggml_cuda_pool_vmm5allocEmPm+0x1d0)[0xe6c52d9eff08]
/usr/lib/ollama/cuda_v13/libggml-cuda.so(_ZN20ggml_cuda_pool_allocI6__halfE5allocEm+0x34)[0xe6c52d9f0894]
/usr/lib/ollama/cuda_v13/libggml-cuda.so(+0x107c48)[0xe6c52d9e7c48]
/usr/lib/ollama/cuda_v13/libggml-cuda.so(+0x10c8a4)[0xe6c52d9ec8a4]
/usr/lib/ollama/cuda_v13/libggml-cuda.so(+0x10e174)[0xe6c52d9ee174]
/usr/bin/ollama(+0x135ba18)[0xbbf9af5aba18]
/usr/bin/ollama(+0x12cd4f8)[0xbbf9af51d4f8]
/usr/bin/ollama(+0x4001cc)[0xbbf9ae6501cc]
SIGABRT: abort
PC=0xe6c5b9667608 m=11 sigcode=18446744073709551610
signal arrived during cgo execution

goroutine 15 gp=0x4000583180 m=11 mp=0x4000581008 [syscall]:
runtime.cgocall(0xbbf9af51d4d0, 0x40000470a8)
      runtime/cgocall.go:167 +0x44 fp=0x4000047060 sp=0x4000047020 pc=0xbbf9ae644d24
github.com/ollama/ollama/ml/backend/ggml._Cfunc_ggml_backend_sched_reserve(0xe6c56d0b8220, 0xe6c2b8a151a0)
      _cgo_gotypes.go:1012 +0x34 fp=0x40000470a0 sp=0x4000047060 pc=0xbbf9aeae3084
github.com/ollama/ollama/ml/backend/ggml.(*Context).Reserve.func2(...)
      github.com/ollama/ollama/ml/backend/ggml/ggml.go:850
github.com/ollama/ollama/ml/backend/ggml.(*Context).Reserve(0x4000536040)
      github.com/ollama/ollama/ml/backend/ggml/ggml.go:850 +0xe0 fp=0x4000047330 sp=0x40000470a0 pc=0xbbf9aeaedc50
github.com/ollama/ollama/runner/ollamarunner.(*Server).reserveWorstCaseGraph(0x40002430e0, 0x1)
      github.com/ollama/ollama/runner/ollamarunner/runner.go:1169 +0x834 fp=0x4000047660 sp=0x4000047330 pc=0xbbf9aebf06e4
github.com/ollama/ollama/runner/ollamarunner.(*Server).allocModel(0x40002430e0, {0xfffffa165dec?, 0x0?}, {0x0, 0x14, {0x4000360080, 0x1, 0x1}, 0x0}, {0x0?, ...}, ...)
      github.com/ollama/ollama/runner/ollamarunner/runner.go:1232 +0x2e4 fp=0x4000047710 sp=0x4000047660 pc=0xbbf9aebf0db4
github.com/ollama/ollama/runner/ollamarunner.(*Server).load(0x40002430e0, {0xbbf9afe7a3e0, 0x400059c000}, 0x4000592000)
      github.com/ollama/ollama/runner/ollamarunner/runner.go:1317 +0x460 fp=0x4000047aa0 sp=0x4000047710 pc=0xbbf9aebf1780
github.com/ollama/ollama/runner/ollamarunner.(*Server).load-fm({0xbbf9afe7a3e0?, 0x400059c000?}, 0x400024db28?)
      <autogenerated>:1 +0x40 fp=0x4000047ad0 sp=0x4000047aa0 pc=0xbbf9aebf3630
net/http.HandlerFunc.ServeHTTP(0x4000553ec0?, {0xbbf9afe7a3e0?, 0x400059c000?}, 0x400024db10?)
      net/http/server.go:2294 +0x38 fp=0x4000047b00 sp=0x4000047ad0 pc=0xbbf9ae90ff78
net/http.(*ServeMux).ServeHTTP(0x10?, {0xbbf9afe7a3e0, 0x400059c000}, 0x4000592000)
      net/http/server.go:2822 +0x1b4 fp=0x4000047b50 sp=0x4000047b00 pc=0xbbf9ae911b04
net/http.serverHandler.ServeHTTP({0xbbf9afe76470?}, {0xbbf9afe7a3e0?, 0x400059c000?}, 0x1?)
      net/http/server.go:3301 +0xbc fp=0x4000047b80 sp=0x4000047b50 pc=0xbbf9ae92d7ec
net/http.(*conn).serve(0x40004ec510, {0xbbf9afe7cc48, 0x400027a2a0})
      net/http/server.go:2102 +0x52c fp=0x4000047fa0 sp=0x4000047b80 pc=0xbbf9ae90e71c
net/http.(*Server).Serve.gowrap3()
      net/http/server.go:3454 +0x30 fp=0x4000047fd0 sp=0x4000047fa0 pc=0xbbf9ae9138e0
runtime.goexit({})
      runtime/asm_arm64.s:1223 +0x4 fp=0x4000047fd0 sp=0x4000047fd0 pc=0xbbf9ae6503d4
created by net/http.(*Server).Serve in goroutine 1
      net/http/server.go:3454 +0x3d8

goroutine 1 gp=0x40000021c0 m=nil [IO wait]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
      runtime/proc.go:435 +0xc8 fp=0x4001705710 sp=0x40017056f0 pc=0xbbf9ae648238
runtime.netpollblock(0x7000000000?, 0x6?, 0x0?)
      runtime/netpoll.go:575 +0x158 fp=0x4001705750 sp=0x4001705710 pc=0xbbf9ae60d028
internal/poll.runtime_pollWait(0xe6c5b9416f30, 0x72)
      runtime/netpoll.go:351 +0xa0 fp=0x4001705780 sp=0x4001705750 pc=0xbbf9ae6473f0
internal/poll.(*pollDesc).wait(0x40004e6900?, 0xbbf9ae6d07f8?, 0x0)
      internal/poll/fd_poll_runtime.go:84 +0x28 fp=0x40017057b0 sp=0x4001705780 pc=0xbbf9ae6c9d98
internal/poll.(*pollDesc).waitRead(...)
      internal/poll/fd_poll_runtime.go:89
internal/poll.(*FD).Accept(0x40004e6900)
      internal/poll/fd_unix.go:620 +0x24c fp=0x4001705860 sp=0x40017057b0 pc=0xbbf9ae6ce66c
net.(*netFD).accept(0x40004e6900)
      net/fd_unix.go:172 +0x28 fp=0x4001705920 sp=0x4001705860 pc=0xbbf9ae73d4d8
net.(*TCPListener).accept(0x4000537780)
      net/tcpsock_posix.go:159 +0x24 fp=0x4001705970 sp=0x4001705920 pc=0xbbf9ae752974
net.(*TCPListener).Accept(0x4000537780)
      net/tcpsock.go:380 +0x2c fp=0x40017059b0 sp=0x4001705970 pc=0xbbf9ae75190c
net/http.(*onceCloseListener).Accept(0x40004ec510?)
      <autogenerated>:1 +0x30 fp=0x40017059d0 sp=0x40017059b0 pc=0xbbf9ae939e10
net/http.(*Server).Serve(0x400050f600, {0xbbf9afe7a200, 0x4000537780})
      net/http/server.go:3424 +0x290 fp=0x4001705b00 sp=0x40017059d0 pc=0xbbf9ae913550
github.com/ollama/ollama/runner/ollamarunner.Execute({0x40000320a0, 0x4, 0x4})
      github.com/ollama/ollama/runner/ollamarunner/runner.go:1453 +0x7fc fp=0x4001705cd0 sp=0x4001705b00 pc=0xbbf9aebf305c
github.com/ollama/ollama/runner.Execute({0x4000032080?, 0x0?, 0x0?})
      github.com/ollama/ollama/runner/runner.go:18 +0x14c fp=0x4001705d10 sp=0x4001705cd0 pc=0xbbf9aec87afc
github.com/ollama/ollama/cmd.NewCLI.func3(0x400050f300?, {0xbbf9af831262?, 0x4?, 0xbbf9af831266?})
      github.com/ollama/ollama/cmd/cmd.go:2277 +0x54 fp=0x4001705d40 sp=0x4001705d10 pc=0xbbf9af39fd14
github.com/spf13/cobra.(*Command).execute(0x40004f1b08, {0x4000539770, 0x5, 0x5})
      github.com/spf13/cobra@v1.7.0/command.go:940 +0x648 fp=0x4001705e60 sp=0x4001705d40 pc=0xbbf9ae7ad1d8
github.com/spf13/cobra.(*Command).ExecuteC(0x40004b4908)
      github.com/spf13/cobra@v1.7.0/command.go:1068 +0x320 fp=0x4001705f20 sp=0x4001705e60 pc=0xbbf9ae7ad920
github.com/spf13/cobra.(*Command).Execute(...)
      github.com/spf13/cobra@v1.7.0/command.go:992
github.com/spf13/cobra.(*Command).ExecuteContext(...)
      github.com/spf13/cobra@v1.7.0/command.go:985
main.main()
      github.com/ollama/ollama/main.go:12 +0x54 fp=0x4001705f40 sp=0x4001705f20 pc=0xbbf9af3a1494
runtime.main()
      runtime/proc.go:283 +0x284 fp=0x4001705fd0 sp=0x4001705f40 pc=0xbbf9ae6143d4
runtime.goexit({})
      runtime/asm_arm64.s:1223 +0x4 fp=0x4001705fd0 sp=0x4001705fd0 pc=0xbbf9ae6503d4

goroutine 2 gp=0x4000002c40 m=nil [force gc (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
      runtime/proc.go:435 +0xc8 fp=0x400008af90 sp=0x400008af70 pc=0xbbf9ae648238
runtime.goparkunlock(...)
      runtime/proc.go:441
runtime.forcegchelper()
      runtime/proc.go:348 +0xb8 fp=0x400008afd0 sp=0x400008af90 pc=0xbbf9ae614728
runtime.goexit({})
      runtime/asm_arm64.s:1223 +0x4 fp=0x400008afd0 sp=0x400008afd0 pc=0xbbf9ae6503d4
created by runtime.init.7 in goroutine 1
      runtime/proc.go:336 +0x24

goroutine 3 gp=0x4000003180 m=nil [GC sweep wait]:
runtime.gopark(0x1?, 0x0?, 0x0?, 0x0?, 0x0?)
      runtime/proc.go:435 +0xc8 fp=0x400008b760 sp=0x400008b740 pc=0xbbf9ae648238
runtime.goparkunlock(...)
      runtime/proc.go:441
runtime.bgsweep(0x40000b6000)
      runtime/mgcsweep.go:316 +0x108 fp=0x400008b7b0 sp=0x400008b760 pc=0xbbf9ae5fef58
runtime.gcenable.gowrap1()
      runtime/mgc.go:204 +0x28 fp=0x400008b7d0 sp=0x400008b7b0 pc=0xbbf9ae5f2d88
runtime.goexit({})
      runtime/asm_arm64.s:1223 +0x4 fp=0x400008b7d0 sp=0x400008b7d0 pc=0xbbf9ae6503d4
created by runtime.gcenable in goroutine 1
      runtime/mgc.go:204 +0x6c

goroutine 4 gp=0x4000003340 m=nil [GC scavenge wait]:
runtime.gopark(0x10000?, 0xbbf9afa58348?, 0x0?, 0x0?, 0x0?)
      runtime/proc.go:435 +0xc8 fp=0x400008bf60 sp=0x400008bf40 pc=0xbbf9ae648238
runtime.goparkunlock(...)
      runtime/proc.go:441
runtime.(*scavengerState).park(0xbbf9b08a3f40)
      runtime/mgcscavenge.go:425 +0x5c fp=0x400008bf90 sp=0x400008bf60 pc=0xbbf9ae5fca1c
runtime.bgscavenge(0x40000b6000)
      runtime/mgcscavenge.go:658 +0xac fp=0x400008bfb0 sp=0x400008bf90 pc=0xbbf9ae5fcf9c
runtime.gcenable.gowrap2()
      runtime/mgc.go:205 +0x28 fp=0x400008bfd0 sp=0x400008bfb0 pc=0xbbf9ae5f2d28
runtime.goexit({})
      runtime/asm_arm64.s:1223 +0x4 fp=0x400008bfd0 sp=0x400008bfd0 pc=0xbbf9ae6503d4
created by runtime.gcenable in goroutine 1
      runtime/mgc.go:205 +0xac

goroutine 5 gp=0x4000003c00 m=nil [finalizer wait]:
runtime.gopark(0x18000001b8?, 0xe6c5b95a8ef0?, 0x8?, 0x1?, 0x1c0?)
      runtime/proc.go:435 +0xc8 fp=0x400008a590 sp=0x400008a570 pc=0xbbf9ae648238
runtime.runfinq()
      runtime/mfinal.go:196 +0x108 fp=0x400008a7d0 sp=0x400008a590 pc=0xbbf9ae5f1d88
runtime.goexit({})
      runtime/asm_arm64.s:1223 +0x4 fp=0x400008a7d0 sp=0x400008a7d0 pc=0xbbf9ae6503d4
created by runtime.createfing in goroutine 1
      runtime/mfinal.go:166 +0x80

goroutine 6 gp=0x40001fa700 m=nil [chan receive]:
runtime.gopark(0x400023f9a0?, 0x4001d4d848?, 0x48?, 0xc7?, 0xbbf9ae7159f8?)
      runtime/proc.go:435 +0xc8 fp=0x400008c6f0 sp=0x400008c6d0 pc=0xbbf9ae648238
runtime.chanrecv(0x400003a380, 0x0, 0x1)
      runtime/chan.go:664 +0x42c fp=0x400008c770 sp=0x400008c6f0 pc=0xbbf9ae5e3dec
runtime.chanrecv1(0x0?, 0x0?)
      runtime/chan.go:506 +0x14 fp=0x400008c7a0 sp=0x400008c770 pc=0xbbf9ae5e3984
runtime.unique_runtime_registerUniqueMapCleanup.func2(...)
      runtime/mgc.go:1796
runtime.unique_runtime_registerUniqueMapCleanup.gowrap1()
      runtime/mgc.go:1799 +0x3c fp=0x400008c7d0 sp=0x400008c7a0 pc=0xbbf9ae5f5fac
runtime.goexit({})
      runtime/asm_arm64.s:1223 +0x4 fp=0x400008c7d0 sp=0x400008c7d0 pc=0xbbf9ae6503d4
created by unique.runtime_registerUniqueMapCleanup in goroutine 1
      runtime/mgc.go:1794 +0x78

goroutine 7 gp=0x40001faa80 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
      runtime/proc.go:435 +0xc8 fp=0x400008cf10 sp=0x400008cef0 pc=0xbbf9ae648238
runtime.gcBgMarkWorker(0x400003b7a0)
      runtime/mgc.go:1423 +0xdc fp=0x400008cfb0 sp=0x400008cf10 pc=0xbbf9ae5f521c
runtime.gcBgMarkStartWorkers.gowrap1()
      runtime/mgc.go:1339 +0x28 fp=0x400008cfd0 sp=0x400008cfb0 pc=0xbbf9ae5f5108
runtime.goexit({})
      runtime/asm_arm64.s:1223 +0x4 fp=0x400008cfd0 sp=0x400008cfd0 pc=0xbbf9ae6503d4
created by runtime.gcBgMarkStartWorkers in goroutine 1
      runtime/mgc.go:1339 +0x140

goroutine 8 gp=0x40001fac40 m=nil [GC worker (idle)]:
runtime.gopark(0xbbf9b0980160?, 0x1?, 0x39?, 0x1f?, 0x0?)
      runtime/proc.go:435 +0xc8 fp=0x400008d710 sp=0x400008d6f0 pc=0xbbf9ae648238
runtime.gcBgMarkWorker(0x400003b7a0)
      runtime/mgc.go:1423 +0xdc fp=0x400008d7b0 sp=0x400008d710 pc=0xbbf9ae5f521c
runtime.gcBgMarkStartWorkers.gowrap1()
      runtime/mgc.go:1339 +0x28 fp=0x400008d7d0 sp=0x400008d7b0 pc=0xbbf9ae5f5108
runtime.goexit({})
      runtime/asm_arm64.s:1223 +0x4 fp=0x400008d7d0 sp=0x400008d7d0 pc=0xbbf9ae6503d4
created by runtime.gcBgMarkStartWorkers in goroutine 1
      runtime/mgc.go:1339 +0x140

goroutine 9 gp=0x40001fae00 m=nil [GC worker (idle)]:
runtime.gopark(0x49818cf5f302?, 0x0?, 0x0?, 0x0?, 0x0?)
      runtime/proc.go:435 +0xc8 fp=0x400008df10 sp=0x400008def0 pc=0xbbf9ae648238
runtime.gcBgMarkWorker(0x400003b7a0)
      runtime/mgc.go:1423 +0xdc fp=0x400008dfb0 sp=0x400008df10 pc=0xbbf9ae5f521c
runtime.gcBgMarkStartWorkers.gowrap1()
      runtime/mgc.go:1339 +0x28 fp=0x400008dfd0 sp=0x400008dfb0 pc=0xbbf9ae5f5108
runtime.goexit({})
      runtime/asm_arm64.s:1223 +0x4 fp=0x400008dfd0 sp=0x400008dfd0 pc=0xbbf9ae6503d4
created by runtime.gcBgMarkStartWorkers in goroutine 1
      runtime/mgc.go:1339 +0x140

goroutine 10 gp=0x40001fafc0 m=nil [GC worker (idle)]:
runtime.gopark(0x49818cf6e442?, 0x0?, 0x0?, 0x0?, 0x0?)
      runtime/proc.go:435 +0xc8 fp=0x4000086710 sp=0x40000866f0 pc=0xbbf9ae648238
runtime.gcBgMarkWorker(0x400003b7a0)
      runtime/mgc.go:1423 +0xdc fp=0x40000867b0 sp=0x4000086710 pc=0xbbf9ae5f521c
runtime.gcBgMarkStartWorkers.gowrap1()
      runtime/mgc.go:1339 +0x28 fp=0x40000867d0 sp=0x40000867b0 pc=0xbbf9ae5f5108
runtime.goexit({})
      runtime/asm_arm64.s:1223 +0x4 fp=0x40000867d0 sp=0x40000867d0 pc=0xbbf9ae6503d4
created by runtime.gcBgMarkStartWorkers in goroutine 1
      runtime/mgc.go:1339 +0x140

goroutine 11 gp=0x40001fb180 m=nil [GC worker (idle)]:
runtime.gopark(0x49818cf6b0b2?, 0x0?, 0x0?, 0x0?, 0x0?)
      runtime/proc.go:435 +0xc8 fp=0x4000086f10 sp=0x4000086ef0 pc=0xbbf9ae648238
runtime.gcBgMarkWorker(0x400003b7a0)
      runtime/mgc.go:1423 +0xdc fp=0x4000086fb0 sp=0x4000086f10 pc=0xbbf9ae5f521c
runtime.gcBgMarkStartWorkers.gowrap1()
      runtime/mgc.go:1339 +0x28 fp=0x4000086fd0 sp=0x4000086fb0 pc=0xbbf9ae5f5108
runtime.goexit({})
      runtime/asm_arm64.s:1223 +0x4 fp=0x4000086fd0 sp=0x4000086fd0 pc=0xbbf9ae6503d4
created by runtime.gcBgMarkStartWorkers in goroutine 1
      runtime/mgc.go:1339 +0x140

goroutine 12 gp=0x40001fb340 m=nil [GC worker (idle)]:
runtime.gopark(0x49818cf679a2?, 0x0?, 0x0?, 0x0?, 0x0?)
      runtime/proc.go:435 +0xc8 fp=0x4000087710 sp=0x40000876f0 pc=0xbbf9ae648238
runtime.gcBgMarkWorker(0x400003b7a0)
      runtime/mgc.go:1423 +0xdc fp=0x40000877b0 sp=0x4000087710 pc=0xbbf9ae5f521c
runtime.gcBgMarkStartWorkers.gowrap1()
      runtime/mgc.go:1339 +0x28 fp=0x40000877d0 sp=0x40000877b0 pc=0xbbf9ae5f5108
runtime.goexit({})
      runtime/asm_arm64.s:1223 +0x4 fp=0x40000877d0 sp=0x40000877d0 pc=0xbbf9ae6503d4
created by runtime.gcBgMarkStartWorkers in goroutine 1
      runtime/mgc.go:1339 +0x140

goroutine 13 gp=0x40001fb500 m=nil [GC worker (idle)]:
runtime.gopark(0x49818cf5e962?, 0x0?, 0x0?, 0x0?, 0x0?)
      runtime/proc.go:435 +0xc8 fp=0x4000087f10 sp=0x4000087ef0 pc=0xbbf9ae648238
runtime.gcBgMarkWorker(0x400003b7a0)
      runtime/mgc.go:1423 +0xdc fp=0x4000087fb0 sp=0x4000087f10 pc=0xbbf9ae5f521c
runtime.gcBgMarkStartWorkers.gowrap1()
      runtime/mgc.go:1339 +0x28 fp=0x4000087fd0 sp=0x4000087fb0 pc=0xbbf9ae5f5108
runtime.goexit({})
      runtime/asm_arm64.s:1223 +0x4 fp=0x4000087fd0 sp=0x4000087fd0 pc=0xbbf9ae6503d4
created by runtime.gcBgMarkStartWorkers in goroutine 1
      runtime/mgc.go:1339 +0x140

goroutine 18 gp=0x4000504000 m=nil [GC worker (idle)]:
runtime.gopark(0xbbf9b0980160?, 0x1?, 0x68?, 0x38?, 0x0?)
      runtime/proc.go:435 +0xc8 fp=0x400050a710 sp=0x400050a6f0 pc=0xbbf9ae648238
runtime.gcBgMarkWorker(0x400003b7a0)
      runtime/mgc.go:1423 +0xdc fp=0x400050a7b0 sp=0x400050a710 pc=0xbbf9ae5f521c
runtime.gcBgMarkStartWorkers.gowrap1()
      runtime/mgc.go:1339 +0x28 fp=0x400050a7d0 sp=0x400050a7b0 pc=0xbbf9ae5f5108
runtime.goexit({})
      runtime/asm_arm64.s:1223 +0x4 fp=0x400050a7d0 sp=0x400050a7d0 pc=0xbbf9ae6503d4
created by runtime.gcBgMarkStartWorkers in goroutine 1
      runtime/mgc.go:1339 +0x140

goroutine 19 gp=0x40005041c0 m=nil [GC worker (idle)]:
runtime.gopark(0x49818cf6de62?, 0x1?, 0x32?, 0x3a?, 0x0?)
      runtime/proc.go:435 +0xc8 fp=0x400050af10 sp=0x400050aef0 pc=0xbbf9ae648238
runtime.gcBgMarkWorker(0x400003b7a0)
      runtime/mgc.go:1423 +0xdc fp=0x400050afb0 sp=0x400050af10 pc=0xbbf9ae5f521c
runtime.gcBgMarkStartWorkers.gowrap1()
      runtime/mgc.go:1339 +0x28 fp=0x400050afd0 sp=0x400050afb0 pc=0xbbf9ae5f5108
runtime.goexit({})
      runtime/asm_arm64.s:1223 +0x4 fp=0x400050afd0 sp=0x400050afd0 pc=0xbbf9ae6503d4
created by runtime.gcBgMarkStartWorkers in goroutine 1
      runtime/mgc.go:1339 +0x140

goroutine 20 gp=0x4000504380 m=nil [GC worker (idle)]:
runtime.gopark(0x49818cf6daa2?, 0x3?, 0x14?, 0xc7?, 0x0?)
      runtime/proc.go:435 +0xc8 fp=0x400050b710 sp=0x400050b6f0 pc=0xbbf9ae648238
runtime.gcBgMarkWorker(0x400003b7a0)
      runtime/mgc.go:1423 +0xdc fp=0x400050b7b0 sp=0x400050b710 pc=0xbbf9ae5f521c
runtime.gcBgMarkStartWorkers.gowrap1()
      runtime/mgc.go:1339 +0x28 fp=0x400050b7d0 sp=0x400050b7b0 pc=0xbbf9ae5f5108
runtime.goexit({})
      runtime/asm_arm64.s:1223 +0x4 fp=0x400050b7d0 sp=0x400050b7d0 pc=0xbbf9ae6503d4
created by runtime.gcBgMarkStartWorkers in goroutine 1
      runtime/mgc.go:1339 +0x140

goroutine 21 gp=0x4000504540 m=nil [GC worker (idle)]:
runtime.gopark(0x49818cf71c52?, 0x0?, 0x0?, 0x0?, 0x0?)
      runtime/proc.go:435 +0xc8 fp=0x400050bf10 sp=0x400050bef0 pc=0xbbf9ae648238
runtime.gcBgMarkWorker(0x400003b7a0)
      runtime/mgc.go:1423 +0xdc fp=0x400050bfb0 sp=0x400050bf10 pc=0xbbf9ae5f521c
runtime.gcBgMarkStartWorkers.gowrap1()
      runtime/mgc.go:1339 +0x28 fp=0x400050bfd0 sp=0x400050bfb0 pc=0xbbf9ae5f5108
runtime.goexit({})
      runtime/asm_arm64.s:1223 +0x4 fp=0x400050bfd0 sp=0x400050bfd0 pc=0xbbf9ae6503d4
created by runtime.gcBgMarkStartWorkers in goroutine 1
      runtime/mgc.go:1339 +0x140

goroutine 22 gp=0x4000504700 m=nil [GC worker (idle)]:
runtime.gopark(0x49818cf57a71?, 0x0?, 0x0?, 0x0?, 0x0?)
      runtime/proc.go:435 +0xc8 fp=0x400050c710 sp=0x400050c6f0 pc=0xbbf9ae648238
runtime.gcBgMarkWorker(0x400003b7a0)
      runtime/mgc.go:1423 +0xdc fp=0x400050c7b0 sp=0x400050c710 pc=0xbbf9ae5f521c
runtime.gcBgMarkStartWorkers.gowrap1()
      runtime/mgc.go:1339 +0x28 fp=0x400050c7d0 sp=0x400050c7b0 pc=0xbbf9ae5f5108
runtime.goexit({})
      runtime/asm_arm64.s:1223 +0x4 fp=0x400050c7d0 sp=0x400050c7d0 pc=0xbbf9ae6503d4
created by runtime.gcBgMarkStartWorkers in goroutine 1
      runtime/mgc.go:1339 +0x140

goroutine 23 gp=0x40005048c0 m=nil [GC worker (idle)]:
runtime.gopark(0x49818cf73c02?, 0x0?, 0x0?, 0x0?, 0x0?)
      runtime/proc.go:435 +0xc8 fp=0x400050cf10 sp=0x400050cef0 pc=0xbbf9ae648238
runtime.gcBgMarkWorker(0x400003b7a0)
      runtime/mgc.go:1423 +0xdc fp=0x400050cfb0 sp=0x400050cf10 pc=0xbbf9ae5f521c
runtime.gcBgMarkStartWorkers.gowrap1()
      runtime/mgc.go:1339 +0x28 fp=0x400050cfd0 sp=0x400050cfb0 pc=0xbbf9ae5f5108
runtime.goexit({})
      runtime/asm_arm64.s:1223 +0x4 fp=0x400050cfd0 sp=0x400050cfd0 pc=0xbbf9ae6503d4
created by runtime.gcBgMarkStartWorkers in goroutine 1
      runtime/mgc.go:1339 +0x140

goroutine 24 gp=0x4000504a80 m=nil [GC worker (idle)]:
runtime.gopark(0x49818cf6ec92?, 0x0?, 0x0?, 0x0?, 0x0?)
      runtime/proc.go:435 +0xc8 fp=0x400050d710 sp=0x400050d6f0 pc=0xbbf9ae648238
runtime.gcBgMarkWorker(0x400003b7a0)
      runtime/mgc.go:1423 +0xdc fp=0x400050d7b0 sp=0x400050d710 pc=0xbbf9ae5f521c
runtime.gcBgMarkStartWorkers.gowrap1()
      runtime/mgc.go:1339 +0x28 fp=0x400050d7d0 sp=0x400050d7b0 pc=0xbbf9ae5f5108
runtime.goexit({})
      runtime/asm_arm64.s:1223 +0x4 fp=0x400050d7d0 sp=0x400050d7d0 pc=0xbbf9ae6503d4
created by runtime.gcBgMarkStartWorkers in goroutine 1
      runtime/mgc.go:1339 +0x140

goroutine 25 gp=0x4000504c40 m=nil [GC worker (idle)]:
runtime.gopark(0x49818cf6b962?, 0x1?, 0x28?, 0x5b?, 0x0?)
      runtime/proc.go:435 +0xc8 fp=0x400050df10 sp=0x400050def0 pc=0xbbf9ae648238
runtime.gcBgMarkWorker(0x400003b7a0)
      runtime/mgc.go:1423 +0xdc fp=0x400050dfb0 sp=0x400050df10 pc=0xbbf9ae5f521c
runtime.gcBgMarkStartWorkers.gowrap1()
      runtime/mgc.go:1339 +0x28 fp=0x400050dfd0 sp=0x400050dfb0 pc=0xbbf9ae5f5108
runtime.goexit({})
      runtime/asm_arm64.s:1223 +0x4 fp=0x400050dfd0 sp=0x400050dfd0 pc=0xbbf9ae6503d4
created by runtime.gcBgMarkStartWorkers in goroutine 1
      runtime/mgc.go:1339 +0x140

goroutine 26 gp=0x4000504e00 m=nil [GC worker (idle)]:
runtime.gopark(0x49818cf66d92?, 0x1?, 0xc1?, 0xa3?, 0x0?)
      runtime/proc.go:435 +0xc8 fp=0x4000506710 sp=0x40005066f0 pc=0xbbf9ae648238
runtime.gcBgMarkWorker(0x400003b7a0)
      runtime/mgc.go:1423 +0xdc fp=0x40005067b0 sp=0x4000506710 pc=0xbbf9ae5f521c
runtime.gcBgMarkStartWorkers.gowrap1()
      runtime/mgc.go:1339 +0x28 fp=0x40005067d0 sp=0x40005067b0 pc=0xbbf9ae5f5108
runtime.goexit({})
      runtime/asm_arm64.s:1223 +0x4 fp=0x40005067d0 sp=0x40005067d0 pc=0xbbf9ae6503d4
created by runtime.gcBgMarkStartWorkers in goroutine 1
      runtime/mgc.go:1339 +0x140

goroutine 34 gp=0x4000102380 m=nil [GC worker (idle)]:
runtime.gopark(0x49818cf6b772?, 0x1?, 0xf3?, 0x7e?, 0x0?)
      runtime/proc.go:435 +0xc8 fp=0x400009af10 sp=0x400009aef0 pc=0xbbf9ae648238
runtime.gcBgMarkWorker(0x400003b7a0)
      runtime/mgc.go:1423 +0xdc fp=0x400009afb0 sp=0x400009af10 pc=0xbbf9ae5f521c
runtime.gcBgMarkStartWorkers.gowrap1()
      runtime/mgc.go:1339 +0x28 fp=0x400009afd0 sp=0x400009afb0 pc=0xbbf9ae5f5108
runtime.goexit({})
      runtime/asm_arm64.s:1223 +0x4 fp=0x400009afd0 sp=0x400009afd0 pc=0xbbf9ae6503d4
created by runtime.gcBgMarkStartWorkers in goroutine 1
      runtime/mgc.go:1339 +0x140

goroutine 35 gp=0x4000102540 m=nil [GC worker (idle)]:
runtime.gopark(0xbbf9b0980160?, 0x3?, 0x64?, 0x55?, 0x0?)
      runtime/proc.go:435 +0xc8 fp=0x400011af10 sp=0x400011aef0 pc=0xbbf9ae648238
runtime.gcBgMarkWorker(0x400003b7a0)
      runtime/mgc.go:1423 +0xdc fp=0x400011afb0 sp=0x400011af10 pc=0xbbf9ae5f521c
runtime.gcBgMarkStartWorkers.gowrap1()
      runtime/mgc.go:1339 +0x28 fp=0x400011afd0 sp=0x400011afb0 pc=0xbbf9ae5f5108
runtime.goexit({})
      runtime/asm_arm64.s:1223 +0x4 fp=0x400011afd0 sp=0x400011afd0 pc=0xbbf9ae6503d4
created by runtime.gcBgMarkStartWorkers in goroutine 1
      runtime/mgc.go:1339 +0x140

goroutine 36 gp=0x4000102700 m=nil [GC worker (idle)]:
runtime.gopark(0x49818cf5ffe2?, 0x3?, 0x12?, 0x5b?, 0x0?)
      runtime/proc.go:435 +0xc8 fp=0x400011b710 sp=0x400011b6f0 pc=0xbbf9ae648238
runtime.gcBgMarkWorker(0x400003b7a0)
      runtime/mgc.go:1423 +0xdc fp=0x400011b7b0 sp=0x400011b710 pc=0xbbf9ae5f521c
runtime.gcBgMarkStartWorkers.gowrap1()
      runtime/mgc.go:1339 +0x28 fp=0x400011b7d0 sp=0x400011b7b0 pc=0xbbf9ae5f5108
runtime.goexit({})
      runtime/asm_arm64.s:1223 +0x4 fp=0x400011b7d0 sp=0x400011b7d0 pc=0xbbf9ae6503d4
created by runtime.gcBgMarkStartWorkers in goroutine 1
      runtime/mgc.go:1339 +0x140

goroutine 37 gp=0x40001028c0 m=nil [GC worker (idle)]:
runtime.gopark(0x49818cf67002?, 0x1?, 0x30?, 0x60?, 0x0?)
      runtime/proc.go:435 +0xc8 fp=0x400011bf10 sp=0x400011bef0 pc=0xbbf9ae648238
runtime.gcBgMarkWorker(0x400003b7a0)
      runtime/mgc.go:1423 +0xdc fp=0x400011bfb0 sp=0x400011bf10 pc=0xbbf9ae5f521c
runtime.gcBgMarkStartWorkers.gowrap1()
      runtime/mgc.go:1339 +0x28 fp=0x400011bfd0 sp=0x400011bfb0 pc=0xbbf9ae5f5108
runtime.goexit({})
      runtime/asm_arm64.s:1223 +0x4 fp=0x400011bfd0 sp=0x400011bfd0 pc=0xbbf9ae6503d4
created by runtime.gcBgMarkStartWorkers in goroutine 1
      runtime/mgc.go:1339 +0x140

goroutine 14 gp=0x4000582fc0 m=nil [sync.WaitGroup.Wait]:
runtime.gopark(0xbbf9b08b6d00?, 0x0?, 0x60?, 0xe0?, 0x0?)
      runtime/proc.go:435 +0xc8 fp=0x400009da90 sp=0x400009da70 pc=0xbbf9ae648238
runtime.goparkunlock(...)
      runtime/proc.go:441
runtime.semacquire1(0x4000243198, 0x0, 0x1, 0x0, 0x18)
      runtime/sema.go:188 +0x204 fp=0x400009dae0 sp=0x400009da90 pc=0xbbf9ae628874
sync.runtime_SemacquireWaitGroup(0x0?)
      runtime/sema.go:110 +0x2c fp=0x400009db20 sp=0x400009dae0 pc=0xbbf9ae649bec
sync.(*WaitGroup).Wait(0x4000243190)
      sync/waitgroup.go:118 +0x70 fp=0x400009db40 sp=0x400009db20 pc=0xbbf9ae65bab0
github.com/ollama/ollama/runner/ollamarunner.(*Server).run(0x40002430e0, {0xbbf9afe7cc80, 0x4000539810})
      github.com/ollama/ollama/runner/ollamarunner/runner.go:442 +0x38 fp=0x400009dfa0 sp=0x400009db40 pc=0xbbf9aebeb368
github.com/ollama/ollama/runner/ollamarunner.Execute.gowrap1()
      github.com/ollama/ollama/runner/ollamarunner/runner.go:1430 +0x30 fp=0x400009dfd0 sp=0x400009dfa0 pc=0xbbf9aebf3280
runtime.goexit({})
      runtime/asm_arm64.s:1223 +0x4 fp=0x400009dfd0 sp=0x400009dfd0 pc=0xbbf9ae6503d4
created by github.com/ollama/ollama/runner/ollamarunner.Execute in goroutine 1
      github.com/ollama/ollama/runner/ollamarunner/runner.go:1430 +0x448

goroutine 50 gp=0x4000102e00 m=nil [IO wait]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
      runtime/proc.go:435 +0xc8 fp=0x400011c580 sp=0x400011c560 pc=0xbbf9ae648238
runtime.netpollblock(0x0?, 0xffffffff?, 0xff?)
      runtime/netpoll.go:575 +0x158 fp=0x400011c5c0 sp=0x400011c580 pc=0xbbf9ae60d028
internal/poll.runtime_pollWait(0xe6c5b9416e18, 0x72)
      runtime/netpoll.go:351 +0xa0 fp=0x400011c5f0 sp=0x400011c5c0 pc=0xbbf9ae6473f0
internal/poll.(*pollDesc).wait(0x40004e6980?, 0x400027a491?, 0x0)
      internal/poll/fd_poll_runtime.go:84 +0x28 fp=0x400011c620 sp=0x400011c5f0 pc=0xbbf9ae6c9d98
internal/poll.(*pollDesc).waitRead(...)
      internal/poll/fd_poll_runtime.go:89
internal/poll.(*FD).Read(0x40004e6980, {0x400027a491, 0x1, 0x1})
      internal/poll/fd_unix.go:165 +0x1fc fp=0x400011c6c0 sp=0x400011c620 pc=0xbbf9ae6cb04c
net.(*netFD).Read(0x40004e6980, {0x400027a491?, 0x0?, 0x0?})
      net/fd_posix.go:55 +0x28 fp=0x400011c710 sp=0x400011c6c0 pc=0xbbf9ae73baa8
net.(*conn).Read(0x4000532710, {0x400027a491?, 0x0?, 0x0?})
      net/net.go:194 +0x34 fp=0x400011c760 sp=0x400011c710 pc=0xbbf9ae7491e4
net/http.(*connReader).backgroundRead(0x400027a480)
      net/http/server.go:690 +0x40 fp=0x400011c7b0 sp=0x400011c760 pc=0xbbf9ae909090
net/http.(*connReader).startBackgroundRead.gowrap2()
      net/http/server.go:686 +0x28 fp=0x400011c7d0 sp=0x400011c7b0 pc=0xbbf9ae908f78
runtime.goexit({})
      runtime/asm_arm64.s:1223 +0x4 fp=0x400011c7d0 sp=0x400011c7d0 pc=0xbbf9ae6503d4
created by net/http.(*connReader).startBackgroundRead in goroutine 15
      net/http/server.go:686 +0xc4

r0      0x0
r1      0x87
r2      0x6
r3      0xe6c559f6f140
r4      0xe6c5b9c13b50
r5      0x1
r6      0x20
r7      0xe6c559f6d860
r8      0x83
r9      0x0
r10     0x6d
r11     0x101010101010101
r12     0xe6c559f6d8f0
r13     0x0
r14     0x1
r15     0xe6c2b8c45060
r16     0x1
r17     0xe6c5b9607d0c
r18     0xe6c2b8aa9bf8
r19     0x87
r20     0xe6c559f6f140
r21     0x6
r22     0xe6c559f6e4e0
r23     0x800000000
r24     0xf0000000
r25     0x1
r26     0x780000
r27     0xe6c2b8c44930
r28     0xe6c2b8c44ef0
r29     0xe6c559f6d7f0
lr      0xe6c5b96675f4
sp      0xe6c559f6d7e0
pc      0xe6c5b9667608
fault   0x0
time=2026-04-07T09:31:43.309Z level=ERROR source=server.go:1207 msg="do load request" error="Post \"http://127.0.0.1:41209/load\": EOF"
time=2026-04-07T09:31:43.310Z level=ERROR source=server.go:1207 msg="do load request" error="Post \"http://127.0.0.1:41209/load\": dial tcp 127.0.0.1:41209: connect: connection refused"
time=2026-04-07T09:31:43.310Z level=INFO source=sched.go:511 msg="Load failed" model=/root/.ollama/models/blobs/sha256-280af6832eca23cb322c4dcc65edfea98a21b8f8ab07dc7553bd6f7e6e7a3313 error="model failed to load, this may be due to resource limitations or an internal error, check ollama server logs for details"
time=2026-04-07T09:31:43.393Z level=ERROR source=server.go:304 msg="llama runner terminated" error="exit status 2"
[GIN] 2026/04/07 - 09:31:43 | 500 |  21.65670961s |      172.19.0.3 | POST     "/api/chat"

<!-- gh-comment-id:4198085799 --> @Bastiendsp commented on GitHub (Apr 7, 2026): Hi, i've the same problems, but here are some logs for u guys : I'm on **Ollama 0.20.3** running on **DGX Spark** **Ubuntu DGX OS** <details> <summary>Logs :</summary> ``` ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no ggml_cuda_init: found 1 CUDA devices: Device 0: NVIDIA GB10, compute capability 12.1, VMM: yes, ID: GPU-a20637ba-815b-7e34-0ad0-6433b297b7cf load_backend: loaded CUDA backend from /usr/lib/ollama/cuda_v13/libggml-cuda.so time=2026-04-07T09:31:22.800Z level=INFO source=ggml.go:104 msg=system CPU.0.NEON=1 CPU.0.ARM_FMA=1 CPU.0.LLAMAFILE=1 CPU.1.NEON=1 CPU.1.ARM_FMA=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=750,800,860,870,890,900,1000,1030,1100,1200,1210 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(clang) time=2026-04-07T09:31:22.804Z level=INFO source=model.go:97 msg="gemma4: token IDs" image=255999 image_end=258882 audio=256000 audio_end=258883 time=2026-04-07T09:31:22.888Z level=INFO source=model.go:138 msg="vision: decode" elapsed=1.294612ms bounds=(0,0)-(2048,2048) time=2026-04-07T09:31:22.961Z level=INFO source=model.go:145 msg="vision: preprocess" elapsed=73.101916ms size="[768 768]" time=2026-04-07T09:31:22.961Z level=INFO source=model.go:148 msg="vision: pixelValues" shape="[768 768 3]" dim0=768 dim1=768 dim2=3 time=2026-04-07T09:31:22.961Z level=INFO source=model.go:152 msg="vision: patches" patchesX=48 patchesY=48 total=2304 patchSize=16 time=2026-04-07T09:31:22.962Z level=INFO source=model.go:156 msg="vision: encoded" elapsed=75.160258ms shape="[5376 256]" /ml/backend/ggml/ggml/src/ggml-cuda/ggml-cuda.cu:560: GGML_ASSERT(pool_size + reserve_size <= CUDA_POOL_VMM_MAX_SIZE) failed /usr/lib/ollama/libggml-base.so.0(+0x23070)[0xe6c559523070] /usr/lib/ollama/libggml-base.so.0(ggml_print_backtrace+0x268)[0xe6c55952304c] /usr/lib/ollama/libggml-base.so.0(ggml_abort+0xe0)[0xe6c559521fe0] /usr/lib/ollama/cuda_v13/libggml-cuda.so(_ZN18ggml_cuda_pool_vmm5allocEmPm+0x1d0)[0xe6c52d9eff08] /usr/lib/ollama/cuda_v13/libggml-cuda.so(_ZN20ggml_cuda_pool_allocI6__halfE5allocEm+0x34)[0xe6c52d9f0894] /usr/lib/ollama/cuda_v13/libggml-cuda.so(+0x107c48)[0xe6c52d9e7c48] /usr/lib/ollama/cuda_v13/libggml-cuda.so(+0x10c8a4)[0xe6c52d9ec8a4] /usr/lib/ollama/cuda_v13/libggml-cuda.so(+0x10e174)[0xe6c52d9ee174] /usr/bin/ollama(+0x135ba18)[0xbbf9af5aba18] /usr/bin/ollama(+0x12cd4f8)[0xbbf9af51d4f8] /usr/bin/ollama(+0x4001cc)[0xbbf9ae6501cc] SIGABRT: abort PC=0xe6c5b9667608 m=11 sigcode=18446744073709551610 signal arrived during cgo execution goroutine 15 gp=0x4000583180 m=11 mp=0x4000581008 [syscall]: runtime.cgocall(0xbbf9af51d4d0, 0x40000470a8) runtime/cgocall.go:167 +0x44 fp=0x4000047060 sp=0x4000047020 pc=0xbbf9ae644d24 github.com/ollama/ollama/ml/backend/ggml._Cfunc_ggml_backend_sched_reserve(0xe6c56d0b8220, 0xe6c2b8a151a0) _cgo_gotypes.go:1012 +0x34 fp=0x40000470a0 sp=0x4000047060 pc=0xbbf9aeae3084 github.com/ollama/ollama/ml/backend/ggml.(*Context).Reserve.func2(...) github.com/ollama/ollama/ml/backend/ggml/ggml.go:850 github.com/ollama/ollama/ml/backend/ggml.(*Context).Reserve(0x4000536040) github.com/ollama/ollama/ml/backend/ggml/ggml.go:850 +0xe0 fp=0x4000047330 sp=0x40000470a0 pc=0xbbf9aeaedc50 github.com/ollama/ollama/runner/ollamarunner.(*Server).reserveWorstCaseGraph(0x40002430e0, 0x1) github.com/ollama/ollama/runner/ollamarunner/runner.go:1169 +0x834 fp=0x4000047660 sp=0x4000047330 pc=0xbbf9aebf06e4 github.com/ollama/ollama/runner/ollamarunner.(*Server).allocModel(0x40002430e0, {0xfffffa165dec?, 0x0?}, {0x0, 0x14, {0x4000360080, 0x1, 0x1}, 0x0}, {0x0?, ...}, ...) github.com/ollama/ollama/runner/ollamarunner/runner.go:1232 +0x2e4 fp=0x4000047710 sp=0x4000047660 pc=0xbbf9aebf0db4 github.com/ollama/ollama/runner/ollamarunner.(*Server).load(0x40002430e0, {0xbbf9afe7a3e0, 0x400059c000}, 0x4000592000) github.com/ollama/ollama/runner/ollamarunner/runner.go:1317 +0x460 fp=0x4000047aa0 sp=0x4000047710 pc=0xbbf9aebf1780 github.com/ollama/ollama/runner/ollamarunner.(*Server).load-fm({0xbbf9afe7a3e0?, 0x400059c000?}, 0x400024db28?) <autogenerated>:1 +0x40 fp=0x4000047ad0 sp=0x4000047aa0 pc=0xbbf9aebf3630 net/http.HandlerFunc.ServeHTTP(0x4000553ec0?, {0xbbf9afe7a3e0?, 0x400059c000?}, 0x400024db10?) net/http/server.go:2294 +0x38 fp=0x4000047b00 sp=0x4000047ad0 pc=0xbbf9ae90ff78 net/http.(*ServeMux).ServeHTTP(0x10?, {0xbbf9afe7a3e0, 0x400059c000}, 0x4000592000) net/http/server.go:2822 +0x1b4 fp=0x4000047b50 sp=0x4000047b00 pc=0xbbf9ae911b04 net/http.serverHandler.ServeHTTP({0xbbf9afe76470?}, {0xbbf9afe7a3e0?, 0x400059c000?}, 0x1?) net/http/server.go:3301 +0xbc fp=0x4000047b80 sp=0x4000047b50 pc=0xbbf9ae92d7ec net/http.(*conn).serve(0x40004ec510, {0xbbf9afe7cc48, 0x400027a2a0}) net/http/server.go:2102 +0x52c fp=0x4000047fa0 sp=0x4000047b80 pc=0xbbf9ae90e71c net/http.(*Server).Serve.gowrap3() net/http/server.go:3454 +0x30 fp=0x4000047fd0 sp=0x4000047fa0 pc=0xbbf9ae9138e0 runtime.goexit({}) runtime/asm_arm64.s:1223 +0x4 fp=0x4000047fd0 sp=0x4000047fd0 pc=0xbbf9ae6503d4 created by net/http.(*Server).Serve in goroutine 1 net/http/server.go:3454 +0x3d8 goroutine 1 gp=0x40000021c0 m=nil [IO wait]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xc8 fp=0x4001705710 sp=0x40017056f0 pc=0xbbf9ae648238 runtime.netpollblock(0x7000000000?, 0x6?, 0x0?) runtime/netpoll.go:575 +0x158 fp=0x4001705750 sp=0x4001705710 pc=0xbbf9ae60d028 internal/poll.runtime_pollWait(0xe6c5b9416f30, 0x72) runtime/netpoll.go:351 +0xa0 fp=0x4001705780 sp=0x4001705750 pc=0xbbf9ae6473f0 internal/poll.(*pollDesc).wait(0x40004e6900?, 0xbbf9ae6d07f8?, 0x0) internal/poll/fd_poll_runtime.go:84 +0x28 fp=0x40017057b0 sp=0x4001705780 pc=0xbbf9ae6c9d98 internal/poll.(*pollDesc).waitRead(...) internal/poll/fd_poll_runtime.go:89 internal/poll.(*FD).Accept(0x40004e6900) internal/poll/fd_unix.go:620 +0x24c fp=0x4001705860 sp=0x40017057b0 pc=0xbbf9ae6ce66c net.(*netFD).accept(0x40004e6900) net/fd_unix.go:172 +0x28 fp=0x4001705920 sp=0x4001705860 pc=0xbbf9ae73d4d8 net.(*TCPListener).accept(0x4000537780) net/tcpsock_posix.go:159 +0x24 fp=0x4001705970 sp=0x4001705920 pc=0xbbf9ae752974 net.(*TCPListener).Accept(0x4000537780) net/tcpsock.go:380 +0x2c fp=0x40017059b0 sp=0x4001705970 pc=0xbbf9ae75190c net/http.(*onceCloseListener).Accept(0x40004ec510?) <autogenerated>:1 +0x30 fp=0x40017059d0 sp=0x40017059b0 pc=0xbbf9ae939e10 net/http.(*Server).Serve(0x400050f600, {0xbbf9afe7a200, 0x4000537780}) net/http/server.go:3424 +0x290 fp=0x4001705b00 sp=0x40017059d0 pc=0xbbf9ae913550 github.com/ollama/ollama/runner/ollamarunner.Execute({0x40000320a0, 0x4, 0x4}) github.com/ollama/ollama/runner/ollamarunner/runner.go:1453 +0x7fc fp=0x4001705cd0 sp=0x4001705b00 pc=0xbbf9aebf305c github.com/ollama/ollama/runner.Execute({0x4000032080?, 0x0?, 0x0?}) github.com/ollama/ollama/runner/runner.go:18 +0x14c fp=0x4001705d10 sp=0x4001705cd0 pc=0xbbf9aec87afc github.com/ollama/ollama/cmd.NewCLI.func3(0x400050f300?, {0xbbf9af831262?, 0x4?, 0xbbf9af831266?}) github.com/ollama/ollama/cmd/cmd.go:2277 +0x54 fp=0x4001705d40 sp=0x4001705d10 pc=0xbbf9af39fd14 github.com/spf13/cobra.(*Command).execute(0x40004f1b08, {0x4000539770, 0x5, 0x5}) github.com/spf13/cobra@v1.7.0/command.go:940 +0x648 fp=0x4001705e60 sp=0x4001705d40 pc=0xbbf9ae7ad1d8 github.com/spf13/cobra.(*Command).ExecuteC(0x40004b4908) github.com/spf13/cobra@v1.7.0/command.go:1068 +0x320 fp=0x4001705f20 sp=0x4001705e60 pc=0xbbf9ae7ad920 github.com/spf13/cobra.(*Command).Execute(...) github.com/spf13/cobra@v1.7.0/command.go:992 github.com/spf13/cobra.(*Command).ExecuteContext(...) github.com/spf13/cobra@v1.7.0/command.go:985 main.main() github.com/ollama/ollama/main.go:12 +0x54 fp=0x4001705f40 sp=0x4001705f20 pc=0xbbf9af3a1494 runtime.main() runtime/proc.go:283 +0x284 fp=0x4001705fd0 sp=0x4001705f40 pc=0xbbf9ae6143d4 runtime.goexit({}) runtime/asm_arm64.s:1223 +0x4 fp=0x4001705fd0 sp=0x4001705fd0 pc=0xbbf9ae6503d4 goroutine 2 gp=0x4000002c40 m=nil [force gc (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xc8 fp=0x400008af90 sp=0x400008af70 pc=0xbbf9ae648238 runtime.goparkunlock(...) runtime/proc.go:441 runtime.forcegchelper() runtime/proc.go:348 +0xb8 fp=0x400008afd0 sp=0x400008af90 pc=0xbbf9ae614728 runtime.goexit({}) runtime/asm_arm64.s:1223 +0x4 fp=0x400008afd0 sp=0x400008afd0 pc=0xbbf9ae6503d4 created by runtime.init.7 in goroutine 1 runtime/proc.go:336 +0x24 goroutine 3 gp=0x4000003180 m=nil [GC sweep wait]: runtime.gopark(0x1?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xc8 fp=0x400008b760 sp=0x400008b740 pc=0xbbf9ae648238 runtime.goparkunlock(...) runtime/proc.go:441 runtime.bgsweep(0x40000b6000) runtime/mgcsweep.go:316 +0x108 fp=0x400008b7b0 sp=0x400008b760 pc=0xbbf9ae5fef58 runtime.gcenable.gowrap1() runtime/mgc.go:204 +0x28 fp=0x400008b7d0 sp=0x400008b7b0 pc=0xbbf9ae5f2d88 runtime.goexit({}) runtime/asm_arm64.s:1223 +0x4 fp=0x400008b7d0 sp=0x400008b7d0 pc=0xbbf9ae6503d4 created by runtime.gcenable in goroutine 1 runtime/mgc.go:204 +0x6c goroutine 4 gp=0x4000003340 m=nil [GC scavenge wait]: runtime.gopark(0x10000?, 0xbbf9afa58348?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xc8 fp=0x400008bf60 sp=0x400008bf40 pc=0xbbf9ae648238 runtime.goparkunlock(...) runtime/proc.go:441 runtime.(*scavengerState).park(0xbbf9b08a3f40) runtime/mgcscavenge.go:425 +0x5c fp=0x400008bf90 sp=0x400008bf60 pc=0xbbf9ae5fca1c runtime.bgscavenge(0x40000b6000) runtime/mgcscavenge.go:658 +0xac fp=0x400008bfb0 sp=0x400008bf90 pc=0xbbf9ae5fcf9c runtime.gcenable.gowrap2() runtime/mgc.go:205 +0x28 fp=0x400008bfd0 sp=0x400008bfb0 pc=0xbbf9ae5f2d28 runtime.goexit({}) runtime/asm_arm64.s:1223 +0x4 fp=0x400008bfd0 sp=0x400008bfd0 pc=0xbbf9ae6503d4 created by runtime.gcenable in goroutine 1 runtime/mgc.go:205 +0xac goroutine 5 gp=0x4000003c00 m=nil [finalizer wait]: runtime.gopark(0x18000001b8?, 0xe6c5b95a8ef0?, 0x8?, 0x1?, 0x1c0?) runtime/proc.go:435 +0xc8 fp=0x400008a590 sp=0x400008a570 pc=0xbbf9ae648238 runtime.runfinq() runtime/mfinal.go:196 +0x108 fp=0x400008a7d0 sp=0x400008a590 pc=0xbbf9ae5f1d88 runtime.goexit({}) runtime/asm_arm64.s:1223 +0x4 fp=0x400008a7d0 sp=0x400008a7d0 pc=0xbbf9ae6503d4 created by runtime.createfing in goroutine 1 runtime/mfinal.go:166 +0x80 goroutine 6 gp=0x40001fa700 m=nil [chan receive]: runtime.gopark(0x400023f9a0?, 0x4001d4d848?, 0x48?, 0xc7?, 0xbbf9ae7159f8?) runtime/proc.go:435 +0xc8 fp=0x400008c6f0 sp=0x400008c6d0 pc=0xbbf9ae648238 runtime.chanrecv(0x400003a380, 0x0, 0x1) runtime/chan.go:664 +0x42c fp=0x400008c770 sp=0x400008c6f0 pc=0xbbf9ae5e3dec runtime.chanrecv1(0x0?, 0x0?) runtime/chan.go:506 +0x14 fp=0x400008c7a0 sp=0x400008c770 pc=0xbbf9ae5e3984 runtime.unique_runtime_registerUniqueMapCleanup.func2(...) runtime/mgc.go:1796 runtime.unique_runtime_registerUniqueMapCleanup.gowrap1() runtime/mgc.go:1799 +0x3c fp=0x400008c7d0 sp=0x400008c7a0 pc=0xbbf9ae5f5fac runtime.goexit({}) runtime/asm_arm64.s:1223 +0x4 fp=0x400008c7d0 sp=0x400008c7d0 pc=0xbbf9ae6503d4 created by unique.runtime_registerUniqueMapCleanup in goroutine 1 runtime/mgc.go:1794 +0x78 goroutine 7 gp=0x40001faa80 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xc8 fp=0x400008cf10 sp=0x400008cef0 pc=0xbbf9ae648238 runtime.gcBgMarkWorker(0x400003b7a0) runtime/mgc.go:1423 +0xdc fp=0x400008cfb0 sp=0x400008cf10 pc=0xbbf9ae5f521c runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x28 fp=0x400008cfd0 sp=0x400008cfb0 pc=0xbbf9ae5f5108 runtime.goexit({}) runtime/asm_arm64.s:1223 +0x4 fp=0x400008cfd0 sp=0x400008cfd0 pc=0xbbf9ae6503d4 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x140 goroutine 8 gp=0x40001fac40 m=nil [GC worker (idle)]: runtime.gopark(0xbbf9b0980160?, 0x1?, 0x39?, 0x1f?, 0x0?) runtime/proc.go:435 +0xc8 fp=0x400008d710 sp=0x400008d6f0 pc=0xbbf9ae648238 runtime.gcBgMarkWorker(0x400003b7a0) runtime/mgc.go:1423 +0xdc fp=0x400008d7b0 sp=0x400008d710 pc=0xbbf9ae5f521c runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x28 fp=0x400008d7d0 sp=0x400008d7b0 pc=0xbbf9ae5f5108 runtime.goexit({}) runtime/asm_arm64.s:1223 +0x4 fp=0x400008d7d0 sp=0x400008d7d0 pc=0xbbf9ae6503d4 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x140 goroutine 9 gp=0x40001fae00 m=nil [GC worker (idle)]: runtime.gopark(0x49818cf5f302?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xc8 fp=0x400008df10 sp=0x400008def0 pc=0xbbf9ae648238 runtime.gcBgMarkWorker(0x400003b7a0) runtime/mgc.go:1423 +0xdc fp=0x400008dfb0 sp=0x400008df10 pc=0xbbf9ae5f521c runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x28 fp=0x400008dfd0 sp=0x400008dfb0 pc=0xbbf9ae5f5108 runtime.goexit({}) runtime/asm_arm64.s:1223 +0x4 fp=0x400008dfd0 sp=0x400008dfd0 pc=0xbbf9ae6503d4 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x140 goroutine 10 gp=0x40001fafc0 m=nil [GC worker (idle)]: runtime.gopark(0x49818cf6e442?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xc8 fp=0x4000086710 sp=0x40000866f0 pc=0xbbf9ae648238 runtime.gcBgMarkWorker(0x400003b7a0) runtime/mgc.go:1423 +0xdc fp=0x40000867b0 sp=0x4000086710 pc=0xbbf9ae5f521c runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x28 fp=0x40000867d0 sp=0x40000867b0 pc=0xbbf9ae5f5108 runtime.goexit({}) runtime/asm_arm64.s:1223 +0x4 fp=0x40000867d0 sp=0x40000867d0 pc=0xbbf9ae6503d4 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x140 goroutine 11 gp=0x40001fb180 m=nil [GC worker (idle)]: runtime.gopark(0x49818cf6b0b2?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xc8 fp=0x4000086f10 sp=0x4000086ef0 pc=0xbbf9ae648238 runtime.gcBgMarkWorker(0x400003b7a0) runtime/mgc.go:1423 +0xdc fp=0x4000086fb0 sp=0x4000086f10 pc=0xbbf9ae5f521c runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x28 fp=0x4000086fd0 sp=0x4000086fb0 pc=0xbbf9ae5f5108 runtime.goexit({}) runtime/asm_arm64.s:1223 +0x4 fp=0x4000086fd0 sp=0x4000086fd0 pc=0xbbf9ae6503d4 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x140 goroutine 12 gp=0x40001fb340 m=nil [GC worker (idle)]: runtime.gopark(0x49818cf679a2?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xc8 fp=0x4000087710 sp=0x40000876f0 pc=0xbbf9ae648238 runtime.gcBgMarkWorker(0x400003b7a0) runtime/mgc.go:1423 +0xdc fp=0x40000877b0 sp=0x4000087710 pc=0xbbf9ae5f521c runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x28 fp=0x40000877d0 sp=0x40000877b0 pc=0xbbf9ae5f5108 runtime.goexit({}) runtime/asm_arm64.s:1223 +0x4 fp=0x40000877d0 sp=0x40000877d0 pc=0xbbf9ae6503d4 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x140 goroutine 13 gp=0x40001fb500 m=nil [GC worker (idle)]: runtime.gopark(0x49818cf5e962?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xc8 fp=0x4000087f10 sp=0x4000087ef0 pc=0xbbf9ae648238 runtime.gcBgMarkWorker(0x400003b7a0) runtime/mgc.go:1423 +0xdc fp=0x4000087fb0 sp=0x4000087f10 pc=0xbbf9ae5f521c runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x28 fp=0x4000087fd0 sp=0x4000087fb0 pc=0xbbf9ae5f5108 runtime.goexit({}) runtime/asm_arm64.s:1223 +0x4 fp=0x4000087fd0 sp=0x4000087fd0 pc=0xbbf9ae6503d4 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x140 goroutine 18 gp=0x4000504000 m=nil [GC worker (idle)]: runtime.gopark(0xbbf9b0980160?, 0x1?, 0x68?, 0x38?, 0x0?) runtime/proc.go:435 +0xc8 fp=0x400050a710 sp=0x400050a6f0 pc=0xbbf9ae648238 runtime.gcBgMarkWorker(0x400003b7a0) runtime/mgc.go:1423 +0xdc fp=0x400050a7b0 sp=0x400050a710 pc=0xbbf9ae5f521c runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x28 fp=0x400050a7d0 sp=0x400050a7b0 pc=0xbbf9ae5f5108 runtime.goexit({}) runtime/asm_arm64.s:1223 +0x4 fp=0x400050a7d0 sp=0x400050a7d0 pc=0xbbf9ae6503d4 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x140 goroutine 19 gp=0x40005041c0 m=nil [GC worker (idle)]: runtime.gopark(0x49818cf6de62?, 0x1?, 0x32?, 0x3a?, 0x0?) runtime/proc.go:435 +0xc8 fp=0x400050af10 sp=0x400050aef0 pc=0xbbf9ae648238 runtime.gcBgMarkWorker(0x400003b7a0) runtime/mgc.go:1423 +0xdc fp=0x400050afb0 sp=0x400050af10 pc=0xbbf9ae5f521c runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x28 fp=0x400050afd0 sp=0x400050afb0 pc=0xbbf9ae5f5108 runtime.goexit({}) runtime/asm_arm64.s:1223 +0x4 fp=0x400050afd0 sp=0x400050afd0 pc=0xbbf9ae6503d4 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x140 goroutine 20 gp=0x4000504380 m=nil [GC worker (idle)]: runtime.gopark(0x49818cf6daa2?, 0x3?, 0x14?, 0xc7?, 0x0?) runtime/proc.go:435 +0xc8 fp=0x400050b710 sp=0x400050b6f0 pc=0xbbf9ae648238 runtime.gcBgMarkWorker(0x400003b7a0) runtime/mgc.go:1423 +0xdc fp=0x400050b7b0 sp=0x400050b710 pc=0xbbf9ae5f521c runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x28 fp=0x400050b7d0 sp=0x400050b7b0 pc=0xbbf9ae5f5108 runtime.goexit({}) runtime/asm_arm64.s:1223 +0x4 fp=0x400050b7d0 sp=0x400050b7d0 pc=0xbbf9ae6503d4 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x140 goroutine 21 gp=0x4000504540 m=nil [GC worker (idle)]: runtime.gopark(0x49818cf71c52?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xc8 fp=0x400050bf10 sp=0x400050bef0 pc=0xbbf9ae648238 runtime.gcBgMarkWorker(0x400003b7a0) runtime/mgc.go:1423 +0xdc fp=0x400050bfb0 sp=0x400050bf10 pc=0xbbf9ae5f521c runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x28 fp=0x400050bfd0 sp=0x400050bfb0 pc=0xbbf9ae5f5108 runtime.goexit({}) runtime/asm_arm64.s:1223 +0x4 fp=0x400050bfd0 sp=0x400050bfd0 pc=0xbbf9ae6503d4 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x140 goroutine 22 gp=0x4000504700 m=nil [GC worker (idle)]: runtime.gopark(0x49818cf57a71?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xc8 fp=0x400050c710 sp=0x400050c6f0 pc=0xbbf9ae648238 runtime.gcBgMarkWorker(0x400003b7a0) runtime/mgc.go:1423 +0xdc fp=0x400050c7b0 sp=0x400050c710 pc=0xbbf9ae5f521c runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x28 fp=0x400050c7d0 sp=0x400050c7b0 pc=0xbbf9ae5f5108 runtime.goexit({}) runtime/asm_arm64.s:1223 +0x4 fp=0x400050c7d0 sp=0x400050c7d0 pc=0xbbf9ae6503d4 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x140 goroutine 23 gp=0x40005048c0 m=nil [GC worker (idle)]: runtime.gopark(0x49818cf73c02?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xc8 fp=0x400050cf10 sp=0x400050cef0 pc=0xbbf9ae648238 runtime.gcBgMarkWorker(0x400003b7a0) runtime/mgc.go:1423 +0xdc fp=0x400050cfb0 sp=0x400050cf10 pc=0xbbf9ae5f521c runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x28 fp=0x400050cfd0 sp=0x400050cfb0 pc=0xbbf9ae5f5108 runtime.goexit({}) runtime/asm_arm64.s:1223 +0x4 fp=0x400050cfd0 sp=0x400050cfd0 pc=0xbbf9ae6503d4 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x140 goroutine 24 gp=0x4000504a80 m=nil [GC worker (idle)]: runtime.gopark(0x49818cf6ec92?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xc8 fp=0x400050d710 sp=0x400050d6f0 pc=0xbbf9ae648238 runtime.gcBgMarkWorker(0x400003b7a0) runtime/mgc.go:1423 +0xdc fp=0x400050d7b0 sp=0x400050d710 pc=0xbbf9ae5f521c runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x28 fp=0x400050d7d0 sp=0x400050d7b0 pc=0xbbf9ae5f5108 runtime.goexit({}) runtime/asm_arm64.s:1223 +0x4 fp=0x400050d7d0 sp=0x400050d7d0 pc=0xbbf9ae6503d4 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x140 goroutine 25 gp=0x4000504c40 m=nil [GC worker (idle)]: runtime.gopark(0x49818cf6b962?, 0x1?, 0x28?, 0x5b?, 0x0?) runtime/proc.go:435 +0xc8 fp=0x400050df10 sp=0x400050def0 pc=0xbbf9ae648238 runtime.gcBgMarkWorker(0x400003b7a0) runtime/mgc.go:1423 +0xdc fp=0x400050dfb0 sp=0x400050df10 pc=0xbbf9ae5f521c runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x28 fp=0x400050dfd0 sp=0x400050dfb0 pc=0xbbf9ae5f5108 runtime.goexit({}) runtime/asm_arm64.s:1223 +0x4 fp=0x400050dfd0 sp=0x400050dfd0 pc=0xbbf9ae6503d4 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x140 goroutine 26 gp=0x4000504e00 m=nil [GC worker (idle)]: runtime.gopark(0x49818cf66d92?, 0x1?, 0xc1?, 0xa3?, 0x0?) runtime/proc.go:435 +0xc8 fp=0x4000506710 sp=0x40005066f0 pc=0xbbf9ae648238 runtime.gcBgMarkWorker(0x400003b7a0) runtime/mgc.go:1423 +0xdc fp=0x40005067b0 sp=0x4000506710 pc=0xbbf9ae5f521c runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x28 fp=0x40005067d0 sp=0x40005067b0 pc=0xbbf9ae5f5108 runtime.goexit({}) runtime/asm_arm64.s:1223 +0x4 fp=0x40005067d0 sp=0x40005067d0 pc=0xbbf9ae6503d4 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x140 goroutine 34 gp=0x4000102380 m=nil [GC worker (idle)]: runtime.gopark(0x49818cf6b772?, 0x1?, 0xf3?, 0x7e?, 0x0?) runtime/proc.go:435 +0xc8 fp=0x400009af10 sp=0x400009aef0 pc=0xbbf9ae648238 runtime.gcBgMarkWorker(0x400003b7a0) runtime/mgc.go:1423 +0xdc fp=0x400009afb0 sp=0x400009af10 pc=0xbbf9ae5f521c runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x28 fp=0x400009afd0 sp=0x400009afb0 pc=0xbbf9ae5f5108 runtime.goexit({}) runtime/asm_arm64.s:1223 +0x4 fp=0x400009afd0 sp=0x400009afd0 pc=0xbbf9ae6503d4 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x140 goroutine 35 gp=0x4000102540 m=nil [GC worker (idle)]: runtime.gopark(0xbbf9b0980160?, 0x3?, 0x64?, 0x55?, 0x0?) runtime/proc.go:435 +0xc8 fp=0x400011af10 sp=0x400011aef0 pc=0xbbf9ae648238 runtime.gcBgMarkWorker(0x400003b7a0) runtime/mgc.go:1423 +0xdc fp=0x400011afb0 sp=0x400011af10 pc=0xbbf9ae5f521c runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x28 fp=0x400011afd0 sp=0x400011afb0 pc=0xbbf9ae5f5108 runtime.goexit({}) runtime/asm_arm64.s:1223 +0x4 fp=0x400011afd0 sp=0x400011afd0 pc=0xbbf9ae6503d4 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x140 goroutine 36 gp=0x4000102700 m=nil [GC worker (idle)]: runtime.gopark(0x49818cf5ffe2?, 0x3?, 0x12?, 0x5b?, 0x0?) runtime/proc.go:435 +0xc8 fp=0x400011b710 sp=0x400011b6f0 pc=0xbbf9ae648238 runtime.gcBgMarkWorker(0x400003b7a0) runtime/mgc.go:1423 +0xdc fp=0x400011b7b0 sp=0x400011b710 pc=0xbbf9ae5f521c runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x28 fp=0x400011b7d0 sp=0x400011b7b0 pc=0xbbf9ae5f5108 runtime.goexit({}) runtime/asm_arm64.s:1223 +0x4 fp=0x400011b7d0 sp=0x400011b7d0 pc=0xbbf9ae6503d4 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x140 goroutine 37 gp=0x40001028c0 m=nil [GC worker (idle)]: runtime.gopark(0x49818cf67002?, 0x1?, 0x30?, 0x60?, 0x0?) runtime/proc.go:435 +0xc8 fp=0x400011bf10 sp=0x400011bef0 pc=0xbbf9ae648238 runtime.gcBgMarkWorker(0x400003b7a0) runtime/mgc.go:1423 +0xdc fp=0x400011bfb0 sp=0x400011bf10 pc=0xbbf9ae5f521c runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x28 fp=0x400011bfd0 sp=0x400011bfb0 pc=0xbbf9ae5f5108 runtime.goexit({}) runtime/asm_arm64.s:1223 +0x4 fp=0x400011bfd0 sp=0x400011bfd0 pc=0xbbf9ae6503d4 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x140 goroutine 14 gp=0x4000582fc0 m=nil [sync.WaitGroup.Wait]: runtime.gopark(0xbbf9b08b6d00?, 0x0?, 0x60?, 0xe0?, 0x0?) runtime/proc.go:435 +0xc8 fp=0x400009da90 sp=0x400009da70 pc=0xbbf9ae648238 runtime.goparkunlock(...) runtime/proc.go:441 runtime.semacquire1(0x4000243198, 0x0, 0x1, 0x0, 0x18) runtime/sema.go:188 +0x204 fp=0x400009dae0 sp=0x400009da90 pc=0xbbf9ae628874 sync.runtime_SemacquireWaitGroup(0x0?) runtime/sema.go:110 +0x2c fp=0x400009db20 sp=0x400009dae0 pc=0xbbf9ae649bec sync.(*WaitGroup).Wait(0x4000243190) sync/waitgroup.go:118 +0x70 fp=0x400009db40 sp=0x400009db20 pc=0xbbf9ae65bab0 github.com/ollama/ollama/runner/ollamarunner.(*Server).run(0x40002430e0, {0xbbf9afe7cc80, 0x4000539810}) github.com/ollama/ollama/runner/ollamarunner/runner.go:442 +0x38 fp=0x400009dfa0 sp=0x400009db40 pc=0xbbf9aebeb368 github.com/ollama/ollama/runner/ollamarunner.Execute.gowrap1() github.com/ollama/ollama/runner/ollamarunner/runner.go:1430 +0x30 fp=0x400009dfd0 sp=0x400009dfa0 pc=0xbbf9aebf3280 runtime.goexit({}) runtime/asm_arm64.s:1223 +0x4 fp=0x400009dfd0 sp=0x400009dfd0 pc=0xbbf9ae6503d4 created by github.com/ollama/ollama/runner/ollamarunner.Execute in goroutine 1 github.com/ollama/ollama/runner/ollamarunner/runner.go:1430 +0x448 goroutine 50 gp=0x4000102e00 m=nil [IO wait]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xc8 fp=0x400011c580 sp=0x400011c560 pc=0xbbf9ae648238 runtime.netpollblock(0x0?, 0xffffffff?, 0xff?) runtime/netpoll.go:575 +0x158 fp=0x400011c5c0 sp=0x400011c580 pc=0xbbf9ae60d028 internal/poll.runtime_pollWait(0xe6c5b9416e18, 0x72) runtime/netpoll.go:351 +0xa0 fp=0x400011c5f0 sp=0x400011c5c0 pc=0xbbf9ae6473f0 internal/poll.(*pollDesc).wait(0x40004e6980?, 0x400027a491?, 0x0) internal/poll/fd_poll_runtime.go:84 +0x28 fp=0x400011c620 sp=0x400011c5f0 pc=0xbbf9ae6c9d98 internal/poll.(*pollDesc).waitRead(...) internal/poll/fd_poll_runtime.go:89 internal/poll.(*FD).Read(0x40004e6980, {0x400027a491, 0x1, 0x1}) internal/poll/fd_unix.go:165 +0x1fc fp=0x400011c6c0 sp=0x400011c620 pc=0xbbf9ae6cb04c net.(*netFD).Read(0x40004e6980, {0x400027a491?, 0x0?, 0x0?}) net/fd_posix.go:55 +0x28 fp=0x400011c710 sp=0x400011c6c0 pc=0xbbf9ae73baa8 net.(*conn).Read(0x4000532710, {0x400027a491?, 0x0?, 0x0?}) net/net.go:194 +0x34 fp=0x400011c760 sp=0x400011c710 pc=0xbbf9ae7491e4 net/http.(*connReader).backgroundRead(0x400027a480) net/http/server.go:690 +0x40 fp=0x400011c7b0 sp=0x400011c760 pc=0xbbf9ae909090 net/http.(*connReader).startBackgroundRead.gowrap2() net/http/server.go:686 +0x28 fp=0x400011c7d0 sp=0x400011c7b0 pc=0xbbf9ae908f78 runtime.goexit({}) runtime/asm_arm64.s:1223 +0x4 fp=0x400011c7d0 sp=0x400011c7d0 pc=0xbbf9ae6503d4 created by net/http.(*connReader).startBackgroundRead in goroutine 15 net/http/server.go:686 +0xc4 r0 0x0 r1 0x87 r2 0x6 r3 0xe6c559f6f140 r4 0xe6c5b9c13b50 r5 0x1 r6 0x20 r7 0xe6c559f6d860 r8 0x83 r9 0x0 r10 0x6d r11 0x101010101010101 r12 0xe6c559f6d8f0 r13 0x0 r14 0x1 r15 0xe6c2b8c45060 r16 0x1 r17 0xe6c5b9607d0c r18 0xe6c2b8aa9bf8 r19 0x87 r20 0xe6c559f6f140 r21 0x6 r22 0xe6c559f6e4e0 r23 0x800000000 r24 0xf0000000 r25 0x1 r26 0x780000 r27 0xe6c2b8c44930 r28 0xe6c2b8c44ef0 r29 0xe6c559f6d7f0 lr 0xe6c5b96675f4 sp 0xe6c559f6d7e0 pc 0xe6c5b9667608 fault 0x0 time=2026-04-07T09:31:43.309Z level=ERROR source=server.go:1207 msg="do load request" error="Post \"http://127.0.0.1:41209/load\": EOF" time=2026-04-07T09:31:43.310Z level=ERROR source=server.go:1207 msg="do load request" error="Post \"http://127.0.0.1:41209/load\": dial tcp 127.0.0.1:41209: connect: connection refused" time=2026-04-07T09:31:43.310Z level=INFO source=sched.go:511 msg="Load failed" model=/root/.ollama/models/blobs/sha256-280af6832eca23cb322c4dcc65edfea98a21b8f8ab07dc7553bd6f7e6e7a3313 error="model failed to load, this may be due to resource limitations or an internal error, check ollama server logs for details" time=2026-04-07T09:31:43.393Z level=ERROR source=server.go:304 msg="llama runner terminated" error="exit status 2" [GIN] 2026/04/07 - 09:31:43 | 500 | 21.65670961s | 172.19.0.3 | POST "/api/chat" ``` </details>
Author
Owner

@rick-github commented on GitHub (Apr 7, 2026):

@Bastiendsp This looks like a different problem. Open a new issue, and include the full log, from the server config line through to the crash dump.

<!-- gh-comment-id:4198169472 --> @rick-github commented on GitHub (Apr 7, 2026): @Bastiendsp This looks like a different problem. Open a new issue, and include the full log, from the `server config` line through to the crash dump.
Author
Owner

@rick-github commented on GitHub (Apr 7, 2026):

@Jigit-ship-it What's the output of:

ollama -v
ollama list gemma4:31b
<!-- gh-comment-id:4198175142 --> @rick-github commented on GitHub (Apr 7, 2026): @Jigit-ship-it What's the output of: ``` ollama -v ollama list gemma4:31b ```
Author
Owner

@Jigit-ship-it commented on GitHub (Apr 7, 2026):

Suddenly it works, I dont understand

<!-- gh-comment-id:4198183201 --> @Jigit-ship-it commented on GitHub (Apr 7, 2026): Suddenly it works, I dont understand
Author
Owner

@rick-github commented on GitHub (Apr 7, 2026):

Running ollama with no arguments in Windows results in the server being launched. It could be that it was just taking a while for the server to become ready.

<!-- gh-comment-id:4198199208 --> @rick-github commented on GitHub (Apr 7, 2026): Running `ollama` with no arguments in Windows results in the server being launched. It could be that it was just taking a while for the server to become ready.
Author
Owner

@epertinez commented on GitHub (Apr 7, 2026):

In my case it works but if I give it a middle size context it starts to go very, very slow. Even with /set nothink.
There is a moment when the DGX (128GB) freezes when I open another chat.

<!-- gh-comment-id:4200138990 --> @epertinez commented on GitHub (Apr 7, 2026): In my case it works but if I give it a middle size context it starts to go very, very slow. Even with /set nothink. There is a moment when the DGX (128GB) freezes when I open another chat.
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#9838