github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-23 06:01:37 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #13829] Error loading model #71116

New Issue
Open
opened 2026-05-05 00:24:32 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-05-05 00:24:32 -05:00
Owner
Copy Link

Originally created by @soncemvo on GitHub (Jan 21, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/13829

What is the issue?

Finetuned qwen3-VL via LlamaFactory, converted from safetensors to gguf via llama.cpp, creating model in ollama is ok, but when i try to run model i got error, pls help

Others models include Qwen3-vl works fine

Relevant log output

Jan 22 05:53:11 ai-nvidia-app01 ollama[4135940]: ggml_backend_cuda_device_get_memory device GPU-f96ee413-bbeb-db0e-f5b5-31cdf6e15749 utilizing NVML memory reporting free: 16721838080 total: 25757220864
Jan 22 05:53:11 ai-nvidia-app01 ollama[4135940]: time=2026-01-22T05:53:11.132+03:00 level=INFO source=sched.go:635 msg="updated VRAM based on existing loaded models" gpu=GPU-f96ee413-bbeb-db0e-f5b5-31cdf6e15749 library=CUDA total="24.0 GiB" available="15.6 GiB"
Jan 22 05:53:11 ai-nvidia-app01 ollama[4135940]: time=2026-01-22T05:53:11.163+03:00 level=INFO source=server.go:245 msg="enabling flash attention"
Jan 22 05:53:11 ai-nvidia-app01 ollama[4135940]: time=2026-01-22T05:53:11.163+03:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --model /usr/share/ollama/.ollama/models/blobs/sha256-710dd9ac870452a8e599b4ed7672db3772d0a685541ff4e6b33d9ae9d2bfa8cb --port 44913"
Jan 22 05:53:11 ai-nvidia-app01 ollama[4135940]: time=2026-01-22T05:53:11.164+03:00 level=INFO source=sched.go:452 msg="system memory" total="31.1 GiB" free="27.2 GiB" free_swap="0 B"
Jan 22 05:53:11 ai-nvidia-app01 ollama[4135940]: time=2026-01-22T05:53:11.164+03:00 level=INFO source=sched.go:459 msg="gpu memory" id=GPU-f96ee413-bbeb-db0e-f5b5-31cdf6e15749 library=CUDA available="15.1 GiB" free="15.6 GiB" minimum="457.0 MiB" overhead="0 B"
Jan 22 05:53:11 ai-nvidia-app01 ollama[4135940]: time=2026-01-22T05:53:11.164+03:00 level=INFO source=server.go:755 msg="loading model" "model layers"=37 requested=-1
Jan 22 05:53:11 ai-nvidia-app01 ollama[4135940]: time=2026-01-22T05:53:11.172+03:00 level=INFO source=runner.go:1405 msg="starting ollama engine"
Jan 22 05:53:11 ai-nvidia-app01 ollama[4135940]: time=2026-01-22T05:53:11.172+03:00 level=INFO source=runner.go:1440 msg="Server listening on 127.0.0.1:44913"
Jan 22 05:53:11 ai-nvidia-app01 ollama[4135940]: time=2026-01-22T05:53:11.175+03:00 level=INFO source=runner.go:1278 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:8192 KvCacheType: NumThreads:8 GPULayers:37[ID:GPU-f96ee413-bbeb-db0e-f5b5-31cdf6e15749 Layers:37(0..36)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
Jan 22 05:53:11 ai-nvidia-app01 ollama[4135940]: time=2026-01-22T05:53:11.191+03:00 level=INFO source=ggml.go:136 msg="" architecture=qwen3vl file_type=BF16 name="Qw3Vl Passport" description="" num_tensors=399 num_key_values=32
Jan 22 05:53:11 ai-nvidia-app01 ollama[4135940]: load_backend: loaded CPU backend from /usr/local/lib/ollama/libggml-cpu-alderlake.so
Jan 22 05:53:11 ai-nvidia-app01 ollama[4135940]: ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
Jan 22 05:53:11 ai-nvidia-app01 ollama[4135940]: ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
Jan 22 05:53:11 ai-nvidia-app01 ollama[4135940]: ggml_cuda_init: found 1 CUDA devices:
Jan 22 05:53:11 ai-nvidia-app01 ollama[4135940]:   Device 0: NVIDIA GeForce RTX 4090, compute capability 8.9, VMM: yes, ID: GPU-f96ee413-bbeb-db0e-f5b5-31cdf6e15749
Jan 22 05:53:11 ai-nvidia-app01 ollama[4135940]: load_backend: loaded CUDA backend from /usr/local/lib/ollama/cuda_v12/libggml-cuda.so
Jan 22 05:53:11 ai-nvidia-app01 ollama[4135940]: time=2026-01-22T05:53:11.258+03:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX_VNNI=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=500,520,600,610,700,750,800,860,890,900,1200 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(gcc)
Jan 22 05:53:11 ai-nvidia-app01 ollama[4135940]: time=2026-01-22T05:53:11.459+03:00 level=INFO source=server.go:3634 msg="http: panic serving 127.0.0.1:38682: runtime error: invalid memory address or nil pointer dereference\ngoroutine 47 [running]:\nnet/http.(*conn).serve.func1()\n\tnet/http/server.go:1947 +0xbe\npanic({0x56032e866be0?, 0x56032f2626f0?})\n\truntime/panic.go:792 +0x132\ngithub.com/ollama/ollama/runner/ollamarunner.(*Server).allocModel.func1()\n\tgithub.com/ollama/ollama/runner/ollamarunner/runner.go:1187 +0x11a\npanic({0x56032e866be0?, 0x56032f2626f0?})\n\truntime/panic.go:792 +0x132\ngithub.com/ollama/ollama/ml/nn.(*Conv3D).Forward(0x0, {0x56032e9f8cd0, 0xc000e68500}, {0x56032ea04920?, 0xc0000107b0?}, 0x10?, 0xc000100808?, 0xc00097f800?, 0xc000047190?, 0x0, ...)\n\tgithub.com/ollama/ollama/ml/nn/convolution.go:25 +0x3a\ngithub.com/ollama/ollama/model/models/qwen3vl.(*VisionModel).Forward(0xc0000fe240, {0x56032e9f8cd0, 0xc000e68500}, {0x56032ea04920, 0xc000010198}, 0xc000e1c000)\n\tgithub.com/ollama/ollama/model/models/qwen3vl/model_vision.go:224 +0x118\ngithub.com/ollama/ollama/model/models/qwen3vl.(*Model).EncodeMultimodal(0xc0001691e0, {0x56032e9f8cd0, 0xc000e68500}, {0xc001a28000, 0x400436, 0x700000})\n\tgithub.com/ollama/ollama/model/models/qwen3vl/model.go:43 +0x14e\ngithub.com/ollama/ollama/runner/ollamarunner.(*Server).reserveWorstCaseGraph(0xc00024f0e0, 0x1)\n\tgithub.com/ollama/ollama/runner/ollamarunner/runner.go:1098 +0x34e\ngithub.com/ollama/ollama/runner/ollamarunner.(*Server).allocModel(0xc00024f0e0, {0x7ffde5ec2d24?, 0x56032d63b3fa?}, {0x0, 0x8, {0xc0000b9580, 0x1, 0x1}, 0x1}, {0x0, ...}, ...)\n\tgithub.com/ollama/ollama/runner/ollamarunner/runner.go:1226 +0x391\ngithub.com/ollama/ollama/runner/ollamarunner.(*Server).load(0xc00024f0e0, {0x56032e9eafc0, 0xc0004b8000}, 0xc0004b2000)\n\tgithub.com/ollama/ollama/runner/ollamarunner/runner.go:1305 +0x54b\nnet/http.HandlerFunc.ServeHTTP(0xc0000ffec0?, {0x56032e9eafc0?, 0xc0004b8000?}, 0xc000259b60?)\n\tnet/http/server.go:2294 +0x29\nnet/http.(*ServeMux).ServeHTTP(0x56032d2eaa85?, {0x56032e9eafc0, 0xc0004b8000}, 0xc0004b2000)\n\tnet/http/server.go:2822 +0x1c4\nnet/http.serverHandler.ServeHTTP({0x56032e9e74b0?}, {0x56032e9eafc0?, 0xc0004b8000?}, 0x1?)\n\tnet/http/server.go:3301 +0x8e\nnet/http.(*conn).serve(0xc00016c480, {0x56032e9ed438, 0xc00016aba0})\n\tnet/http/server.go:2102 +0x625\ncreated by net/http.(*Server).Serve in goroutine 1\n\tnet/http/server.go:3454 +0x485"
Jan 22 05:53:11 ai-nvidia-app01 ollama[4135940]: time=2026-01-22T05:53:11.460+03:00 level=INFO source=runner.go:1278 msg=load request="{Operation:close LoraPath:[] Parallel:0 BatchSize:0 FlashAttention:Disabled KvSize:0 KvCacheType: NumThreads:0 GPULayers:[] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
Jan 22 05:53:11 ai-nvidia-app01 ollama[4135940]: time=2026-01-22T05:53:11.460+03:00 level=INFO source=sched.go:479 msg="Load failed" model=/usr/share/ollama/.ollama/models/blobs/sha256-710dd9ac870452a8e599b4ed7672db3772d0a685541ff4e6b33d9ae9d2bfa8cb error="do load request: Post \"http://127.0.0.1:44913/load\": EOF"
Jan 22 05:53:11 ai-nvidia-app01 ollama[4135940]: time=2026-01-22T05:53:11.470+03:00 level=ERROR source=server.go:302 msg="llama runner terminated" error="signal: killed"

OS

Linux

GPU

Nvidia

CPU

Intel

Ollama version

latest

Originally created by @soncemvo on GitHub (Jan 21, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/13829 ### What is the issue? Finetuned qwen3-VL via LlamaFactory, converted from safetensors to gguf via llama.cpp, creating model in ollama is ok, but when i try to run model i got error, pls help Others models include Qwen3-vl works fine ### Relevant log output ```shell Jan 22 05:53:11 ai-nvidia-app01 ollama[4135940]: ggml_backend_cuda_device_get_memory device GPU-f96ee413-bbeb-db0e-f5b5-31cdf6e15749 utilizing NVML memory reporting free: 16721838080 total: 25757220864 Jan 22 05:53:11 ai-nvidia-app01 ollama[4135940]: time=2026-01-22T05:53:11.132+03:00 level=INFO source=sched.go:635 msg="updated VRAM based on existing loaded models" gpu=GPU-f96ee413-bbeb-db0e-f5b5-31cdf6e15749 library=CUDA total="24.0 GiB" available="15.6 GiB" Jan 22 05:53:11 ai-nvidia-app01 ollama[4135940]: time=2026-01-22T05:53:11.163+03:00 level=INFO source=server.go:245 msg="enabling flash attention" Jan 22 05:53:11 ai-nvidia-app01 ollama[4135940]: time=2026-01-22T05:53:11.163+03:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --model /usr/share/ollama/.ollama/models/blobs/sha256-710dd9ac870452a8e599b4ed7672db3772d0a685541ff4e6b33d9ae9d2bfa8cb --port 44913" Jan 22 05:53:11 ai-nvidia-app01 ollama[4135940]: time=2026-01-22T05:53:11.164+03:00 level=INFO source=sched.go:452 msg="system memory" total="31.1 GiB" free="27.2 GiB" free_swap="0 B" Jan 22 05:53:11 ai-nvidia-app01 ollama[4135940]: time=2026-01-22T05:53:11.164+03:00 level=INFO source=sched.go:459 msg="gpu memory" id=GPU-f96ee413-bbeb-db0e-f5b5-31cdf6e15749 library=CUDA available="15.1 GiB" free="15.6 GiB" minimum="457.0 MiB" overhead="0 B" Jan 22 05:53:11 ai-nvidia-app01 ollama[4135940]: time=2026-01-22T05:53:11.164+03:00 level=INFO source=server.go:755 msg="loading model" "model layers"=37 requested=-1 Jan 22 05:53:11 ai-nvidia-app01 ollama[4135940]: time=2026-01-22T05:53:11.172+03:00 level=INFO source=runner.go:1405 msg="starting ollama engine" Jan 22 05:53:11 ai-nvidia-app01 ollama[4135940]: time=2026-01-22T05:53:11.172+03:00 level=INFO source=runner.go:1440 msg="Server listening on 127.0.0.1:44913" Jan 22 05:53:11 ai-nvidia-app01 ollama[4135940]: time=2026-01-22T05:53:11.175+03:00 level=INFO source=runner.go:1278 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:8192 KvCacheType: NumThreads:8 GPULayers:37[ID:GPU-f96ee413-bbeb-db0e-f5b5-31cdf6e15749 Layers:37(0..36)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" Jan 22 05:53:11 ai-nvidia-app01 ollama[4135940]: time=2026-01-22T05:53:11.191+03:00 level=INFO source=ggml.go:136 msg="" architecture=qwen3vl file_type=BF16 name="Qw3Vl Passport" description="" num_tensors=399 num_key_values=32 Jan 22 05:53:11 ai-nvidia-app01 ollama[4135940]: load_backend: loaded CPU backend from /usr/local/lib/ollama/libggml-cpu-alderlake.so Jan 22 05:53:11 ai-nvidia-app01 ollama[4135940]: ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no Jan 22 05:53:11 ai-nvidia-app01 ollama[4135940]: ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no Jan 22 05:53:11 ai-nvidia-app01 ollama[4135940]: ggml_cuda_init: found 1 CUDA devices: Jan 22 05:53:11 ai-nvidia-app01 ollama[4135940]: Device 0: NVIDIA GeForce RTX 4090, compute capability 8.9, VMM: yes, ID: GPU-f96ee413-bbeb-db0e-f5b5-31cdf6e15749 Jan 22 05:53:11 ai-nvidia-app01 ollama[4135940]: load_backend: loaded CUDA backend from /usr/local/lib/ollama/cuda_v12/libggml-cuda.so Jan 22 05:53:11 ai-nvidia-app01 ollama[4135940]: time=2026-01-22T05:53:11.258+03:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX_VNNI=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=500,520,600,610,700,750,800,860,890,900,1200 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(gcc) Jan 22 05:53:11 ai-nvidia-app01 ollama[4135940]: time=2026-01-22T05:53:11.459+03:00 level=INFO source=server.go:3634 msg="http: panic serving 127.0.0.1:38682: runtime error: invalid memory address or nil pointer dereference\ngoroutine 47 [running]:\nnet/http.(*conn).serve.func1()\n\tnet/http/server.go:1947 +0xbe\npanic({0x56032e866be0?, 0x56032f2626f0?})\n\truntime/panic.go:792 +0x132\ngithub.com/ollama/ollama/runner/ollamarunner.(*Server).allocModel.func1()\n\tgithub.com/ollama/ollama/runner/ollamarunner/runner.go:1187 +0x11a\npanic({0x56032e866be0?, 0x56032f2626f0?})\n\truntime/panic.go:792 +0x132\ngithub.com/ollama/ollama/ml/nn.(*Conv3D).Forward(0x0, {0x56032e9f8cd0, 0xc000e68500}, {0x56032ea04920?, 0xc0000107b0?}, 0x10?, 0xc000100808?, 0xc00097f800?, 0xc000047190?, 0x0, ...)\n\tgithub.com/ollama/ollama/ml/nn/convolution.go:25 +0x3a\ngithub.com/ollama/ollama/model/models/qwen3vl.(*VisionModel).Forward(0xc0000fe240, {0x56032e9f8cd0, 0xc000e68500}, {0x56032ea04920, 0xc000010198}, 0xc000e1c000)\n\tgithub.com/ollama/ollama/model/models/qwen3vl/model_vision.go:224 +0x118\ngithub.com/ollama/ollama/model/models/qwen3vl.(*Model).EncodeMultimodal(0xc0001691e0, {0x56032e9f8cd0, 0xc000e68500}, {0xc001a28000, 0x400436, 0x700000})\n\tgithub.com/ollama/ollama/model/models/qwen3vl/model.go:43 +0x14e\ngithub.com/ollama/ollama/runner/ollamarunner.(*Server).reserveWorstCaseGraph(0xc00024f0e0, 0x1)\n\tgithub.com/ollama/ollama/runner/ollamarunner/runner.go:1098 +0x34e\ngithub.com/ollama/ollama/runner/ollamarunner.(*Server).allocModel(0xc00024f0e0, {0x7ffde5ec2d24?, 0x56032d63b3fa?}, {0x0, 0x8, {0xc0000b9580, 0x1, 0x1}, 0x1}, {0x0, ...}, ...)\n\tgithub.com/ollama/ollama/runner/ollamarunner/runner.go:1226 +0x391\ngithub.com/ollama/ollama/runner/ollamarunner.(*Server).load(0xc00024f0e0, {0x56032e9eafc0, 0xc0004b8000}, 0xc0004b2000)\n\tgithub.com/ollama/ollama/runner/ollamarunner/runner.go:1305 +0x54b\nnet/http.HandlerFunc.ServeHTTP(0xc0000ffec0?, {0x56032e9eafc0?, 0xc0004b8000?}, 0xc000259b60?)\n\tnet/http/server.go:2294 +0x29\nnet/http.(*ServeMux).ServeHTTP(0x56032d2eaa85?, {0x56032e9eafc0, 0xc0004b8000}, 0xc0004b2000)\n\tnet/http/server.go:2822 +0x1c4\nnet/http.serverHandler.ServeHTTP({0x56032e9e74b0?}, {0x56032e9eafc0?, 0xc0004b8000?}, 0x1?)\n\tnet/http/server.go:3301 +0x8e\nnet/http.(*conn).serve(0xc00016c480, {0x56032e9ed438, 0xc00016aba0})\n\tnet/http/server.go:2102 +0x625\ncreated by net/http.(*Server).Serve in goroutine 1\n\tnet/http/server.go:3454 +0x485" Jan 22 05:53:11 ai-nvidia-app01 ollama[4135940]: time=2026-01-22T05:53:11.460+03:00 level=INFO source=runner.go:1278 msg=load request="{Operation:close LoraPath:[] Parallel:0 BatchSize:0 FlashAttention:Disabled KvSize:0 KvCacheType: NumThreads:0 GPULayers:[] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" Jan 22 05:53:11 ai-nvidia-app01 ollama[4135940]: time=2026-01-22T05:53:11.460+03:00 level=INFO source=sched.go:479 msg="Load failed" model=/usr/share/ollama/.ollama/models/blobs/sha256-710dd9ac870452a8e599b4ed7672db3772d0a685541ff4e6b33d9ae9d2bfa8cb error="do load request: Post \"http://127.0.0.1:44913/load\": EOF" Jan 22 05:53:11 ai-nvidia-app01 ollama[4135940]: time=2026-01-22T05:53:11.470+03:00 level=ERROR source=server.go:302 msg="llama runner terminated" error="signal: killed" ``` ### OS Linux ### GPU Nvidia ### CPU Intel ### Ollama version latest
GiteaMirror added the bug label 2026-05-05 00:24:32 -05:00
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#71116
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?