github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-16 13:19:40 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #11303] qwen3:8b - CUDA error: the resource allocation failed #7455

New Issue
Open
opened 2026-04-12 19:31:51 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-04-12 19:31:51 -05:00
Owner
Copy Link

Originally created by @sguergachi on GitHub (Jul 5, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/11303

What is the issue?

I have tried everything I could find, but I'm stuck with this issue.

Whenever I try loading qwen3:8B I run into "CUDA error: the resource allocation failed" even though I seem to have a good amount of VRAM headroom on my RTX 3080
Image

When I run llama3.1:8b it seems to run fine.

Relevant log output

llama_model_load: vocab only - skipping tensors
time=2025-07-05T00:23:37.685-04:00 level=INFO source=server.go:438 msg="starting llama server" cmd="C:\\Users\\Sammy\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --model E:\\ollama-models\\blobs\\sha256-a3de86cd1c132c822487ededd47a324c50491393e6565cd14bafa40d0b8e686f --ctx-size 1048 --batch-size 512 --n-gpu-layers 37 --threads 6 --flash-attn --kv-cache-type q4_0 --no-mmap --parallel 1 --port 65430"
time=2025-07-05T00:23:37.689-04:00 level=INFO source=sched.go:483 msg="loaded runners" count=1
time=2025-07-05T00:23:37.689-04:00 level=INFO source=server.go:598 msg="waiting for llama runner to start responding"
time=2025-07-05T00:23:37.690-04:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server error"
time=2025-07-05T00:23:37.737-04:00 level=INFO source=runner.go:815 msg="starting go runner"
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 GeForce RTX 3080, compute capability 8.6, VMM: yes
load_backend: loaded CUDA backend from C:\Users\Sammy\AppData\Local\Programs\Ollama\lib\ollama\ggml-cuda.dll
load_backend: loaded CPU backend from C:\Users\Sammy\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-haswell.dll
time=2025-07-05T00:23:37.856-04:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=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=500,600,610,700,750,800,860,870,890,900,1200 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(clang)
time=2025-07-05T00:23:37.857-04:00 level=INFO source=runner.go:874 msg="Server listening on 127.0.0.1:65430"
llama_model_load_from_file_impl: using device CUDA0 (NVIDIA GeForce RTX 3080) - 9073 MiB free
time=2025-07-05T00:23:37.941-04:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server loading model"
llama_model_loader: loaded meta data with 28 key-value pairs and 399 tensors from E:\ollama-models\blobs\sha256-a3de86cd1c132c822487ededd47a324c50491393e6565cd14bafa40d0b8e686f (version GGUF V3 (latest))
llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
llama_model_loader: - kv   0:                       general.architecture str              = qwen3
llama_model_loader: - kv   1:                               general.type str              = model
llama_model_loader: - kv   2:                               general.name str              = Qwen3 8B
llama_model_loader: - kv   3:                           general.basename str              = Qwen3
llama_model_loader: - kv   4:                         general.size_label str              = 8B
llama_model_loader: - kv   5:                            general.license str              = apache-2.0
llama_model_loader: - kv   6:                          qwen3.block_count u32              = 36
llama_model_loader: - kv   7:                       qwen3.context_length u32              = 40960
llama_model_loader: - kv   8:                     qwen3.embedding_length u32              = 4096
llama_model_loader: - kv   9:                  qwen3.feed_forward_length u32              = 12288
llama_model_loader: - kv  10:                 qwen3.attention.head_count u32              = 32
llama_model_loader: - kv  11:              qwen3.attention.head_count_kv u32              = 8
llama_model_loader: - kv  12:                       qwen3.rope.freq_base f32              = 1000000.000000
llama_model_loader: - kv  13:     qwen3.attention.layer_norm_rms_epsilon f32              = 0.000001
llama_model_loader: - kv  14:                 qwen3.attention.key_length u32              = 128
llama_model_loader: - kv  15:               qwen3.attention.value_length u32              = 128
llama_model_loader: - kv  16:                       tokenizer.ggml.model str              = gpt2
llama_model_loader: - kv  17:                         tokenizer.ggml.pre str              = qwen2
llama_model_loader: - kv  18:                      tokenizer.ggml.tokens arr[str,151936]  = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv  19:                  tokenizer.ggml.token_type arr[i32,151936]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv  20:                      tokenizer.ggml.merges arr[str,151387]  = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
llama_model_loader: - kv  21:                tokenizer.ggml.eos_token_id u32              = 151645
llama_model_loader: - kv  22:            tokenizer.ggml.padding_token_id u32              = 151643
llama_model_loader: - kv  23:                tokenizer.ggml.bos_token_id u32              = 151643
llama_model_loader: - kv  24:               tokenizer.ggml.add_bos_token bool             = false
llama_model_loader: - kv  25:                    tokenizer.chat_template str              = {%- if tools %}\n    {{- '<|im_start|>...
llama_model_loader: - kv  26:               general.quantization_version u32              = 2
llama_model_loader: - kv  27:                          general.file_type u32              = 15
llama_model_loader: - type  f32:  145 tensors
llama_model_loader: - type  f16:   36 tensors
llama_model_loader: - type q4_K:  199 tensors
llama_model_loader: - type q6_K:   19 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type   = Q4_K - Medium
print_info: file size   = 4.86 GiB (5.10 BPW) 
load: special tokens cache size = 26
load: token to piece cache size = 0.9311 MB
print_info: arch             = qwen3
print_info: vocab_only       = 0
print_info: n_ctx_train      = 40960
print_info: n_embd           = 4096
print_info: n_layer          = 36
print_info: n_head           = 32
print_info: n_head_kv        = 8
print_info: n_rot            = 128
print_info: n_swa            = 0
print_info: n_swa_pattern    = 1
print_info: n_embd_head_k    = 128
print_info: n_embd_head_v    = 128
print_info: n_gqa            = 4
print_info: n_embd_k_gqa     = 1024
print_info: n_embd_v_gqa     = 1024
print_info: f_norm_eps       = 0.0e+00
print_info: f_norm_rms_eps   = 1.0e-06
print_info: f_clamp_kqv      = 0.0e+00
print_info: f_max_alibi_bias = 0.0e+00
print_info: f_logit_scale    = 0.0e+00
print_info: f_attn_scale     = 0.0e+00
print_info: n_ff             = 12288
print_info: n_expert         = 0
print_info: n_expert_used    = 0
print_info: causal attn      = 1
print_info: pooling type     = 0
print_info: rope type        = 2
print_info: rope scaling     = linear
print_info: freq_base_train  = 1000000.0
print_info: freq_scale_train = 1
print_info: n_ctx_orig_yarn  = 40960
print_info: rope_finetuned   = unknown
print_info: ssm_d_conv       = 0
print_info: ssm_d_inner      = 0
print_info: ssm_d_state      = 0
print_info: ssm_dt_rank      = 0
print_info: ssm_dt_b_c_rms   = 0
print_info: model type       = 8B
print_info: model params     = 8.19 B
print_info: general.name     = Qwen3 8B
print_info: vocab type       = BPE
print_info: n_vocab          = 151936
print_info: n_merges         = 151387
print_info: BOS token        = 151643 '<|endoftext|>'
print_info: EOS token        = 151645 '<|im_end|>'
print_info: EOT token        = 151645 '<|im_end|>'
print_info: PAD token        = 151643 '<|endoftext|>'
print_info: LF token         = 198 'Ċ'
print_info: FIM PRE token    = 151659 '<|fim_prefix|>'
print_info: FIM SUF token    = 151661 '<|fim_suffix|>'
print_info: FIM MID token    = 151660 '<|fim_middle|>'
print_info: FIM PAD token    = 151662 '<|fim_pad|>'
print_info: FIM REP token    = 151663 '<|repo_name|>'
print_info: FIM SEP token    = 151664 '<|file_sep|>'
print_info: EOG token        = 151643 '<|endoftext|>'
print_info: EOG token        = 151645 '<|im_end|>'
print_info: EOG token        = 151662 '<|fim_pad|>'
print_info: EOG token        = 151663 '<|repo_name|>'
print_info: EOG token        = 151664 '<|file_sep|>'
print_info: max token length = 256
load_tensors: loading model tensors, this can take a while... (mmap = false)
load_tensors: offloading 36 repeating layers to GPU
load_tensors: offloading output layer to GPU
load_tensors: offloaded 37/37 layers to GPU
load_tensors:          CPU model buffer size =   333.84 MiB
load_tensors:        CUDA0 model buffer size =  4643.78 MiB
llama_context: constructing llama_context
llama_context: n_seq_max     = 1
llama_context: n_ctx         = 1048
llama_context: n_ctx_per_seq = 1048
llama_context: n_batch       = 512
llama_context: n_ubatch      = 512
llama_context: causal_attn   = 1
llama_context: flash_attn    = 1
llama_context: freq_base     = 1000000.0
llama_context: freq_scale    = 1
llama_context: n_ctx_per_seq (1048) < n_ctx_train (40960) -- the full capacity of the model will not be utilized
llama_context:  CUDA_Host  output buffer size =     0.60 MiB
llama_kv_cache_unified: kv_size = 1280, type_k = 'q4_0', type_v = 'q4_0', n_layer = 36, can_shift = 1, padding = 256
llama_kv_cache_unified:      CUDA0 KV buffer size =    50.62 MiB
llama_kv_cache_unified: KV self size  =   50.62 MiB, K (q4_0):   25.31 MiB, V (q4_0):   25.31 MiB
llama_context:      CUDA0 compute buffer size =   304.75 MiB
llama_context:  CUDA_Host compute buffer size =    10.51 MiB
llama_context: graph nodes  = 1231
llama_context: graph splits = 2
time=2025-07-05T00:24:38.333-04:00 level=INFO source=server.go:637 msg="llama runner started in 60.64 seconds"
[GIN] 2025/07/05 - 00:24:38 | 200 |          1m1s |       127.0.0.1 | POST     "/api/generate"
CUDA error: the resource allocation failed
  current device: 0, in function cublas_handle at C:/a/ollama/ollama/ml/backend/ggml/ggml/src\ggml-cuda/common.cuh:823
  cublasCreate_v2(&cublas_handles[device])
C:\a\ollama\ollama\ml\backend\ggml\ggml\src\ggml-cuda\ggml-cuda.cu:76: CUDA error
time=2025-07-05T00:24:54.932-04:00 level=ERROR source=server.go:807 msg="post predict" error="Post \"http://127.0.0.1:65430/completion\": read tcp 127.0.0.1:65432->127.0.0.1:65430: wsarecv: An existing connection was forcibly closed by the remote host."
[GIN] 2025/07/05 - 00:24:54 | 200 |   12.3861672s |       127.0.0.1 | POST     "/api/chat"
time=2025-07-05T00:24:55.000-04:00 level=ERROR source=server.go:464 msg="llama runner terminated" error="exit status 0xc0000409"
time=2025-07-05T00:27:12.679-04:00 level=INFO source=routes.go:1235 msg="server config" env="map[CUDA_VISIBLE_DEVICES:0 GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:1048 OLLAMA_DEBUG:DEBUG OLLAMA_FLASH_ATTENTION:true OLLAMA_GPU_OVERHEAD:1 OLLAMA_HOST:http://0.0.0.0:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE:q4_0 OLLAMA_LLM_LIBRARY:cuda OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:1 OLLAMA_MAX_QUEUE:256 OLLAMA_MODELS:E:\\ollama-models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:1 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://* vscode-file://*] OLLAMA_SCHED_SPREAD:true ROCR_VISIBLE_DEVICES:]"
time=2025-07-05T00:27:12.685-04:00 level=INFO source=images.go:476 msg="total blobs: 27"
time=2025-07-05T00:27:12.687-04:00 level=INFO source=images.go:483 msg="total unused blobs removed: 0"
time=2025-07-05T00:27:12.689-04:00 level=INFO source=routes.go:1288 msg="Listening on [::]:11434 (version 0.9.5)"
time=2025-07-05T00:27:12.689-04:00 level=DEBUG source=sched.go:108 msg="starting llm scheduler"
time=2025-07-05T00:27:12.689-04:00 level=INFO source=gpu.go:217 msg="looking for compatible GPUs"
time=2025-07-05T00:27:12.689-04:00 level=INFO source=gpu_windows.go:167 msg=packages count=1
time=2025-07-05T00:27:12.689-04:00 level=INFO source=gpu_windows.go:214 msg="" package=0 cores=6 efficiency=0 threads=12
time=2025-07-05T00:27:12.689-04:00 level=DEBUG source=gpu.go:98 msg="searching for GPU discovery libraries for NVIDIA"
time=2025-07-05T00:27:12.689-04:00 level=DEBUG source=gpu.go:501 msg="Searching for GPU library" name=nvml.dll
time=2025-07-05T00:27:12.689-04:00 level=DEBUG source=gpu.go:525 msg="gpu library search" globs="[C:\\Users\\Sammy\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\nvml.dll C:\\Program Files\\Microsoft MPI\\Bin\\nvml.dll C:\\Program Files\\Eclipse Adoptium\\jdk-21.0.3.9-hotspot\\bin\\nvml.dll C:\\WINDOWS\\system32\\nvml.dll C:\\WINDOWS\\nvml.dll C:\\WINDOWS\\System32\\Wbem\\nvml.dll C:\\WINDOWS\\System32\\WindowsPowerShell\\v1.0\\nvml.dll C:\\WINDOWS\\System32\\OpenSSH\\nvml.dll C:\\Program Files (x86)\\oh-my-posh\\bin\\nvml.dll C:\\Program Files\\NVIDIA Corporation\\NVIDIA App\\NvDLISR\\nvml.dll C:\\Program Files (x86)\\NVIDIA Corporation\\PhysX\\Common\\nvml.dll C:\\Program Files\\dotnet\\nvml.dll C:\\Program Files\\Git\\cmd\\nvml.dll C:\\Program Files\\Docker\\Docker\\resources\\bin\\nvml.dll C:\\Users\\Sammy\\AppData\\Local\\Programs\\oh-my-posh\\bin\\nvml.dll C:\\Users\\Sammy\\AppData\\Local\\Programs\\Python\\Python312\\Scripts\\nvml.dll C:\\Users\\Sammy\\AppData\\Local\\Programs\\Python\\Python312\\nvml.dll C:\\Users\\Sammy\\AppData\\Local\\Programs\\Python\\Launcher\\nvml.dll C:\\Users\\Sammy\\AppData\\Local\\Microsoft\\WindowsApps\\nvml.dll C:\\Users\\Sammy\\AppData\\Local\\Programs\\Microsoft VS Code\\bin\\nvml.dll C:\\Users\\Sammy\\AppData\\Local\\Programs\\Ollama\\nvml.dll C:\\Users\\Sammy\\.cache\\lm-studio\\bin\\nvml.dll c:\\Windows\\System32\\nvml.dll]"
time=2025-07-05T00:27:12.691-04:00 level=DEBUG source=gpu.go:529 msg="skipping PhysX cuda library path" path="C:\\Program Files (x86)\\NVIDIA Corporation\\PhysX\\Common\\nvml.dll"
time=2025-07-05T00:27:12.691-04:00 level=DEBUG source=gpu.go:558 msg="discovered GPU libraries" paths="[C:\\WINDOWS\\system32\\nvml.dll c:\\Windows\\System32\\nvml.dll]"
time=2025-07-05T00:27:12.713-04:00 level=DEBUG source=gpu.go:111 msg="nvidia-ml loaded" library=C:\WINDOWS\system32\nvml.dll
time=2025-07-05T00:27:12.713-04:00 level=DEBUG source=gpu.go:501 msg="Searching for GPU library" name=nvcuda.dll
time=2025-07-05T00:27:12.713-04:00 level=DEBUG source=gpu.go:525 msg="gpu library search" globs="[C:\\Users\\Sammy\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\nvcuda.dll C:\\Program Files\\Microsoft MPI\\Bin\\nvcuda.dll C:\\Program Files\\Eclipse Adoptium\\jdk-21.0.3.9-hotspot\\bin\\nvcuda.dll C:\\WINDOWS\\system32\\nvcuda.dll C:\\WINDOWS\\nvcuda.dll C:\\WINDOWS\\System32\\Wbem\\nvcuda.dll C:\\WINDOWS\\System32\\WindowsPowerShell\\v1.0\\nvcuda.dll C:\\WINDOWS\\System32\\OpenSSH\\nvcuda.dll C:\\Program Files (x86)\\oh-my-posh\\bin\\nvcuda.dll C:\\Program Files\\NVIDIA Corporation\\NVIDIA App\\NvDLISR\\nvcuda.dll C:\\Program Files (x86)\\NVIDIA Corporation\\PhysX\\Common\\nvcuda.dll C:\\Program Files\\dotnet\\nvcuda.dll C:\\Program Files\\Git\\cmd\\nvcuda.dll C:\\Program Files\\Docker\\Docker\\resources\\bin\\nvcuda.dll C:\\Users\\Sammy\\AppData\\Local\\Programs\\oh-my-posh\\bin\\nvcuda.dll C:\\Users\\Sammy\\AppData\\Local\\Programs\\Python\\Python312\\Scripts\\nvcuda.dll C:\\Users\\Sammy\\AppData\\Local\\Programs\\Python\\Python312\\nvcuda.dll C:\\Users\\Sammy\\AppData\\Local\\Programs\\Python\\Launcher\\nvcuda.dll C:\\Users\\Sammy\\AppData\\Local\\Microsoft\\WindowsApps\\nvcuda.dll C:\\Users\\Sammy\\AppData\\Local\\Programs\\Microsoft VS Code\\bin\\nvcuda.dll C:\\Users\\Sammy\\AppData\\Local\\Programs\\Ollama\\nvcuda.dll C:\\Users\\Sammy\\.cache\\lm-studio\\bin\\nvcuda.dll c:\\windows\\system*\\nvcuda.dll]"
time=2025-07-05T00:27:12.715-04:00 level=DEBUG source=gpu.go:529 msg="skipping PhysX cuda library path" path="C:\\Program Files (x86)\\NVIDIA Corporation\\PhysX\\Common\\nvcuda.dll"
time=2025-07-05T00:27:12.716-04:00 level=DEBUG source=gpu.go:558 msg="discovered GPU libraries" paths=[C:\WINDOWS\system32\nvcuda.dll]
initializing C:\WINDOWS\system32\nvcuda.dll
dlsym: cuInit - 00007FF806AA1F80
dlsym: cuDriverGetVersion - 00007FF806AA2020
dlsym: cuDeviceGetCount - 00007FF806AA2816
dlsym: cuDeviceGet - 00007FF806AA2810
dlsym: cuDeviceGetAttribute - 00007FF806AA2170
dlsym: cuDeviceGetUuid - 00007FF806AA2822
dlsym: cuDeviceGetName - 00007FF806AA281C
dlsym: cuCtxCreate_v3 - 00007FF806AA2894
dlsym: cuMemGetInfo_v2 - 00007FF806AA2996
dlsym: cuCtxDestroy - 00007FF806AA28A6
calling cuInit
calling cuDriverGetVersion
raw version 0x2f3a
CUDA driver version: 12.9
calling cuDeviceGetCount
device count 1
time=2025-07-05T00:27:12.747-04:00 level=DEBUG source=gpu.go:125 msg="detected GPUs" count=1 library=C:\WINDOWS\system32\nvcuda.dll
[GPU-4e1a5fb7-791d-60d6-ad53-758e0ef65b3e] CUDA totalMem 10239mb
[GPU-4e1a5fb7-791d-60d6-ad53-758e0ef65b3e] CUDA freeMem 9073mb
[GPU-4e1a5fb7-791d-60d6-ad53-758e0ef65b3e] Compute Capability 8.6
time=2025-07-05T00:27:12.874-04:00 level=DEBUG source=amd_windows.go:34 msg="unable to load amdhip64_6.dll, please make sure to upgrade to the latest amd driver: The specified module could not be found."
releasing cuda driver library
releasing nvml library
time=2025-07-05T00:27:12.875-04:00 level=INFO source=types.go:130 msg="inference compute" id=GPU-4e1a5fb7-791d-60d6-ad53-758e0ef65b3e library=cuda variant=v12 compute=8.6 driver=12.9 name="NVIDIA GeForce RTX 3080" total="10.0 GiB" available="8.9 GiB"

OS

Windows

GPU

Nvidia

CPU

Intel

Ollama version

0.9.5

Originally created by @sguergachi on GitHub (Jul 5, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/11303 ### What is the issue? I have tried everything I could find, but I'm stuck with this issue. Whenever I try loading qwen3:8B I run into "CUDA error: the resource allocation failed" even though I seem to have a good amount of VRAM headroom on my RTX 3080 <img width="924" height="830" alt="Image" src="https://github.com/user-attachments/assets/e63fcc65-c386-4cf5-a65a-800cf8702524" /> When I run llama3.1:8b it seems to run fine. ### Relevant log output ```shell llama_model_load: vocab only - skipping tensors time=2025-07-05T00:23:37.685-04:00 level=INFO source=server.go:438 msg="starting llama server" cmd="C:\\Users\\Sammy\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --model E:\\ollama-models\\blobs\\sha256-a3de86cd1c132c822487ededd47a324c50491393e6565cd14bafa40d0b8e686f --ctx-size 1048 --batch-size 512 --n-gpu-layers 37 --threads 6 --flash-attn --kv-cache-type q4_0 --no-mmap --parallel 1 --port 65430" time=2025-07-05T00:23:37.689-04:00 level=INFO source=sched.go:483 msg="loaded runners" count=1 time=2025-07-05T00:23:37.689-04:00 level=INFO source=server.go:598 msg="waiting for llama runner to start responding" time=2025-07-05T00:23:37.690-04:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server error" time=2025-07-05T00:23:37.737-04:00 level=INFO source=runner.go:815 msg="starting go runner" 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 GeForce RTX 3080, compute capability 8.6, VMM: yes load_backend: loaded CUDA backend from C:\Users\Sammy\AppData\Local\Programs\Ollama\lib\ollama\ggml-cuda.dll load_backend: loaded CPU backend from C:\Users\Sammy\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-haswell.dll time=2025-07-05T00:23:37.856-04:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=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=500,600,610,700,750,800,860,870,890,900,1200 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(clang) time=2025-07-05T00:23:37.857-04:00 level=INFO source=runner.go:874 msg="Server listening on 127.0.0.1:65430" llama_model_load_from_file_impl: using device CUDA0 (NVIDIA GeForce RTX 3080) - 9073 MiB free time=2025-07-05T00:23:37.941-04:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server loading model" llama_model_loader: loaded meta data with 28 key-value pairs and 399 tensors from E:\ollama-models\blobs\sha256-a3de86cd1c132c822487ededd47a324c50491393e6565cd14bafa40d0b8e686f (version GGUF V3 (latest)) llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output. llama_model_loader: - kv 0: general.architecture str = qwen3 llama_model_loader: - kv 1: general.type str = model llama_model_loader: - kv 2: general.name str = Qwen3 8B llama_model_loader: - kv 3: general.basename str = Qwen3 llama_model_loader: - kv 4: general.size_label str = 8B llama_model_loader: - kv 5: general.license str = apache-2.0 llama_model_loader: - kv 6: qwen3.block_count u32 = 36 llama_model_loader: - kv 7: qwen3.context_length u32 = 40960 llama_model_loader: - kv 8: qwen3.embedding_length u32 = 4096 llama_model_loader: - kv 9: qwen3.feed_forward_length u32 = 12288 llama_model_loader: - kv 10: qwen3.attention.head_count u32 = 32 llama_model_loader: - kv 11: qwen3.attention.head_count_kv u32 = 8 llama_model_loader: - kv 12: qwen3.rope.freq_base f32 = 1000000.000000 llama_model_loader: - kv 13: qwen3.attention.layer_norm_rms_epsilon f32 = 0.000001 llama_model_loader: - kv 14: qwen3.attention.key_length u32 = 128 llama_model_loader: - kv 15: qwen3.attention.value_length u32 = 128 llama_model_loader: - kv 16: tokenizer.ggml.model str = gpt2 llama_model_loader: - kv 17: tokenizer.ggml.pre str = qwen2 llama_model_loader: - kv 18: tokenizer.ggml.tokens arr[str,151936] = ["!", "\"", "#", "$", "%", "&", "'", ... llama_model_loader: - kv 19: tokenizer.ggml.token_type arr[i32,151936] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 20: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",... llama_model_loader: - kv 21: tokenizer.ggml.eos_token_id u32 = 151645 llama_model_loader: - kv 22: tokenizer.ggml.padding_token_id u32 = 151643 llama_model_loader: - kv 23: tokenizer.ggml.bos_token_id u32 = 151643 llama_model_loader: - kv 24: tokenizer.ggml.add_bos_token bool = false llama_model_loader: - kv 25: tokenizer.chat_template str = {%- if tools %}\n {{- '<|im_start|>... llama_model_loader: - kv 26: general.quantization_version u32 = 2 llama_model_loader: - kv 27: general.file_type u32 = 15 llama_model_loader: - type f32: 145 tensors llama_model_loader: - type f16: 36 tensors llama_model_loader: - type q4_K: 199 tensors llama_model_loader: - type q6_K: 19 tensors print_info: file format = GGUF V3 (latest) print_info: file type = Q4_K - Medium print_info: file size = 4.86 GiB (5.10 BPW) load: special tokens cache size = 26 load: token to piece cache size = 0.9311 MB print_info: arch = qwen3 print_info: vocab_only = 0 print_info: n_ctx_train = 40960 print_info: n_embd = 4096 print_info: n_layer = 36 print_info: n_head = 32 print_info: n_head_kv = 8 print_info: n_rot = 128 print_info: n_swa = 0 print_info: n_swa_pattern = 1 print_info: n_embd_head_k = 128 print_info: n_embd_head_v = 128 print_info: n_gqa = 4 print_info: n_embd_k_gqa = 1024 print_info: n_embd_v_gqa = 1024 print_info: f_norm_eps = 0.0e+00 print_info: f_norm_rms_eps = 1.0e-06 print_info: f_clamp_kqv = 0.0e+00 print_info: f_max_alibi_bias = 0.0e+00 print_info: f_logit_scale = 0.0e+00 print_info: f_attn_scale = 0.0e+00 print_info: n_ff = 12288 print_info: n_expert = 0 print_info: n_expert_used = 0 print_info: causal attn = 1 print_info: pooling type = 0 print_info: rope type = 2 print_info: rope scaling = linear print_info: freq_base_train = 1000000.0 print_info: freq_scale_train = 1 print_info: n_ctx_orig_yarn = 40960 print_info: rope_finetuned = unknown print_info: ssm_d_conv = 0 print_info: ssm_d_inner = 0 print_info: ssm_d_state = 0 print_info: ssm_dt_rank = 0 print_info: ssm_dt_b_c_rms = 0 print_info: model type = 8B print_info: model params = 8.19 B print_info: general.name = Qwen3 8B print_info: vocab type = BPE print_info: n_vocab = 151936 print_info: n_merges = 151387 print_info: BOS token = 151643 '<|endoftext|>' print_info: EOS token = 151645 '<|im_end|>' print_info: EOT token = 151645 '<|im_end|>' print_info: PAD token = 151643 '<|endoftext|>' print_info: LF token = 198 'Ċ' print_info: FIM PRE token = 151659 '<|fim_prefix|>' print_info: FIM SUF token = 151661 '<|fim_suffix|>' print_info: FIM MID token = 151660 '<|fim_middle|>' print_info: FIM PAD token = 151662 '<|fim_pad|>' print_info: FIM REP token = 151663 '<|repo_name|>' print_info: FIM SEP token = 151664 '<|file_sep|>' print_info: EOG token = 151643 '<|endoftext|>' print_info: EOG token = 151645 '<|im_end|>' print_info: EOG token = 151662 '<|fim_pad|>' print_info: EOG token = 151663 '<|repo_name|>' print_info: EOG token = 151664 '<|file_sep|>' print_info: max token length = 256 load_tensors: loading model tensors, this can take a while... (mmap = false) load_tensors: offloading 36 repeating layers to GPU load_tensors: offloading output layer to GPU load_tensors: offloaded 37/37 layers to GPU load_tensors: CPU model buffer size = 333.84 MiB load_tensors: CUDA0 model buffer size = 4643.78 MiB llama_context: constructing llama_context llama_context: n_seq_max = 1 llama_context: n_ctx = 1048 llama_context: n_ctx_per_seq = 1048 llama_context: n_batch = 512 llama_context: n_ubatch = 512 llama_context: causal_attn = 1 llama_context: flash_attn = 1 llama_context: freq_base = 1000000.0 llama_context: freq_scale = 1 llama_context: n_ctx_per_seq (1048) < n_ctx_train (40960) -- the full capacity of the model will not be utilized llama_context: CUDA_Host output buffer size = 0.60 MiB llama_kv_cache_unified: kv_size = 1280, type_k = 'q4_0', type_v = 'q4_0', n_layer = 36, can_shift = 1, padding = 256 llama_kv_cache_unified: CUDA0 KV buffer size = 50.62 MiB llama_kv_cache_unified: KV self size = 50.62 MiB, K (q4_0): 25.31 MiB, V (q4_0): 25.31 MiB llama_context: CUDA0 compute buffer size = 304.75 MiB llama_context: CUDA_Host compute buffer size = 10.51 MiB llama_context: graph nodes = 1231 llama_context: graph splits = 2 time=2025-07-05T00:24:38.333-04:00 level=INFO source=server.go:637 msg="llama runner started in 60.64 seconds" [GIN] 2025/07/05 - 00:24:38 | 200 | 1m1s | 127.0.0.1 | POST "/api/generate" CUDA error: the resource allocation failed current device: 0, in function cublas_handle at C:/a/ollama/ollama/ml/backend/ggml/ggml/src\ggml-cuda/common.cuh:823 cublasCreate_v2(&cublas_handles[device]) C:\a\ollama\ollama\ml\backend\ggml\ggml\src\ggml-cuda\ggml-cuda.cu:76: CUDA error time=2025-07-05T00:24:54.932-04:00 level=ERROR source=server.go:807 msg="post predict" error="Post \"http://127.0.0.1:65430/completion\": read tcp 127.0.0.1:65432->127.0.0.1:65430: wsarecv: An existing connection was forcibly closed by the remote host." [GIN] 2025/07/05 - 00:24:54 | 200 | 12.3861672s | 127.0.0.1 | POST "/api/chat" time=2025-07-05T00:24:55.000-04:00 level=ERROR source=server.go:464 msg="llama runner terminated" error="exit status 0xc0000409" time=2025-07-05T00:27:12.679-04:00 level=INFO source=routes.go:1235 msg="server config" env="map[CUDA_VISIBLE_DEVICES:0 GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:1048 OLLAMA_DEBUG:DEBUG OLLAMA_FLASH_ATTENTION:true OLLAMA_GPU_OVERHEAD:1 OLLAMA_HOST:http://0.0.0.0:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE:q4_0 OLLAMA_LLM_LIBRARY:cuda OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:1 OLLAMA_MAX_QUEUE:256 OLLAMA_MODELS:E:\\ollama-models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:1 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://* vscode-file://*] OLLAMA_SCHED_SPREAD:true ROCR_VISIBLE_DEVICES:]" time=2025-07-05T00:27:12.685-04:00 level=INFO source=images.go:476 msg="total blobs: 27" time=2025-07-05T00:27:12.687-04:00 level=INFO source=images.go:483 msg="total unused blobs removed: 0" time=2025-07-05T00:27:12.689-04:00 level=INFO source=routes.go:1288 msg="Listening on [::]:11434 (version 0.9.5)" time=2025-07-05T00:27:12.689-04:00 level=DEBUG source=sched.go:108 msg="starting llm scheduler" time=2025-07-05T00:27:12.689-04:00 level=INFO source=gpu.go:217 msg="looking for compatible GPUs" time=2025-07-05T00:27:12.689-04:00 level=INFO source=gpu_windows.go:167 msg=packages count=1 time=2025-07-05T00:27:12.689-04:00 level=INFO source=gpu_windows.go:214 msg="" package=0 cores=6 efficiency=0 threads=12 time=2025-07-05T00:27:12.689-04:00 level=DEBUG source=gpu.go:98 msg="searching for GPU discovery libraries for NVIDIA" time=2025-07-05T00:27:12.689-04:00 level=DEBUG source=gpu.go:501 msg="Searching for GPU library" name=nvml.dll time=2025-07-05T00:27:12.689-04:00 level=DEBUG source=gpu.go:525 msg="gpu library search" globs="[C:\\Users\\Sammy\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\nvml.dll C:\\Program Files\\Microsoft MPI\\Bin\\nvml.dll C:\\Program Files\\Eclipse Adoptium\\jdk-21.0.3.9-hotspot\\bin\\nvml.dll C:\\WINDOWS\\system32\\nvml.dll C:\\WINDOWS\\nvml.dll C:\\WINDOWS\\System32\\Wbem\\nvml.dll C:\\WINDOWS\\System32\\WindowsPowerShell\\v1.0\\nvml.dll C:\\WINDOWS\\System32\\OpenSSH\\nvml.dll C:\\Program Files (x86)\\oh-my-posh\\bin\\nvml.dll C:\\Program Files\\NVIDIA Corporation\\NVIDIA App\\NvDLISR\\nvml.dll C:\\Program Files (x86)\\NVIDIA Corporation\\PhysX\\Common\\nvml.dll C:\\Program Files\\dotnet\\nvml.dll C:\\Program Files\\Git\\cmd\\nvml.dll C:\\Program Files\\Docker\\Docker\\resources\\bin\\nvml.dll C:\\Users\\Sammy\\AppData\\Local\\Programs\\oh-my-posh\\bin\\nvml.dll C:\\Users\\Sammy\\AppData\\Local\\Programs\\Python\\Python312\\Scripts\\nvml.dll C:\\Users\\Sammy\\AppData\\Local\\Programs\\Python\\Python312\\nvml.dll C:\\Users\\Sammy\\AppData\\Local\\Programs\\Python\\Launcher\\nvml.dll C:\\Users\\Sammy\\AppData\\Local\\Microsoft\\WindowsApps\\nvml.dll C:\\Users\\Sammy\\AppData\\Local\\Programs\\Microsoft VS Code\\bin\\nvml.dll C:\\Users\\Sammy\\AppData\\Local\\Programs\\Ollama\\nvml.dll C:\\Users\\Sammy\\.cache\\lm-studio\\bin\\nvml.dll c:\\Windows\\System32\\nvml.dll]" time=2025-07-05T00:27:12.691-04:00 level=DEBUG source=gpu.go:529 msg="skipping PhysX cuda library path" path="C:\\Program Files (x86)\\NVIDIA Corporation\\PhysX\\Common\\nvml.dll" time=2025-07-05T00:27:12.691-04:00 level=DEBUG source=gpu.go:558 msg="discovered GPU libraries" paths="[C:\\WINDOWS\\system32\\nvml.dll c:\\Windows\\System32\\nvml.dll]" time=2025-07-05T00:27:12.713-04:00 level=DEBUG source=gpu.go:111 msg="nvidia-ml loaded" library=C:\WINDOWS\system32\nvml.dll time=2025-07-05T00:27:12.713-04:00 level=DEBUG source=gpu.go:501 msg="Searching for GPU library" name=nvcuda.dll time=2025-07-05T00:27:12.713-04:00 level=DEBUG source=gpu.go:525 msg="gpu library search" globs="[C:\\Users\\Sammy\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\nvcuda.dll C:\\Program Files\\Microsoft MPI\\Bin\\nvcuda.dll C:\\Program Files\\Eclipse Adoptium\\jdk-21.0.3.9-hotspot\\bin\\nvcuda.dll C:\\WINDOWS\\system32\\nvcuda.dll C:\\WINDOWS\\nvcuda.dll C:\\WINDOWS\\System32\\Wbem\\nvcuda.dll C:\\WINDOWS\\System32\\WindowsPowerShell\\v1.0\\nvcuda.dll C:\\WINDOWS\\System32\\OpenSSH\\nvcuda.dll C:\\Program Files (x86)\\oh-my-posh\\bin\\nvcuda.dll C:\\Program Files\\NVIDIA Corporation\\NVIDIA App\\NvDLISR\\nvcuda.dll C:\\Program Files (x86)\\NVIDIA Corporation\\PhysX\\Common\\nvcuda.dll C:\\Program Files\\dotnet\\nvcuda.dll C:\\Program Files\\Git\\cmd\\nvcuda.dll C:\\Program Files\\Docker\\Docker\\resources\\bin\\nvcuda.dll C:\\Users\\Sammy\\AppData\\Local\\Programs\\oh-my-posh\\bin\\nvcuda.dll C:\\Users\\Sammy\\AppData\\Local\\Programs\\Python\\Python312\\Scripts\\nvcuda.dll C:\\Users\\Sammy\\AppData\\Local\\Programs\\Python\\Python312\\nvcuda.dll C:\\Users\\Sammy\\AppData\\Local\\Programs\\Python\\Launcher\\nvcuda.dll C:\\Users\\Sammy\\AppData\\Local\\Microsoft\\WindowsApps\\nvcuda.dll C:\\Users\\Sammy\\AppData\\Local\\Programs\\Microsoft VS Code\\bin\\nvcuda.dll C:\\Users\\Sammy\\AppData\\Local\\Programs\\Ollama\\nvcuda.dll C:\\Users\\Sammy\\.cache\\lm-studio\\bin\\nvcuda.dll c:\\windows\\system*\\nvcuda.dll]" time=2025-07-05T00:27:12.715-04:00 level=DEBUG source=gpu.go:529 msg="skipping PhysX cuda library path" path="C:\\Program Files (x86)\\NVIDIA Corporation\\PhysX\\Common\\nvcuda.dll" time=2025-07-05T00:27:12.716-04:00 level=DEBUG source=gpu.go:558 msg="discovered GPU libraries" paths=[C:\WINDOWS\system32\nvcuda.dll] initializing C:\WINDOWS\system32\nvcuda.dll dlsym: cuInit - 00007FF806AA1F80 dlsym: cuDriverGetVersion - 00007FF806AA2020 dlsym: cuDeviceGetCount - 00007FF806AA2816 dlsym: cuDeviceGet - 00007FF806AA2810 dlsym: cuDeviceGetAttribute - 00007FF806AA2170 dlsym: cuDeviceGetUuid - 00007FF806AA2822 dlsym: cuDeviceGetName - 00007FF806AA281C dlsym: cuCtxCreate_v3 - 00007FF806AA2894 dlsym: cuMemGetInfo_v2 - 00007FF806AA2996 dlsym: cuCtxDestroy - 00007FF806AA28A6 calling cuInit calling cuDriverGetVersion raw version 0x2f3a CUDA driver version: 12.9 calling cuDeviceGetCount device count 1 time=2025-07-05T00:27:12.747-04:00 level=DEBUG source=gpu.go:125 msg="detected GPUs" count=1 library=C:\WINDOWS\system32\nvcuda.dll [GPU-4e1a5fb7-791d-60d6-ad53-758e0ef65b3e] CUDA totalMem 10239mb [GPU-4e1a5fb7-791d-60d6-ad53-758e0ef65b3e] CUDA freeMem 9073mb [GPU-4e1a5fb7-791d-60d6-ad53-758e0ef65b3e] Compute Capability 8.6 time=2025-07-05T00:27:12.874-04:00 level=DEBUG source=amd_windows.go:34 msg="unable to load amdhip64_6.dll, please make sure to upgrade to the latest amd driver: The specified module could not be found." releasing cuda driver library releasing nvml library time=2025-07-05T00:27:12.875-04:00 level=INFO source=types.go:130 msg="inference compute" id=GPU-4e1a5fb7-791d-60d6-ad53-758e0ef65b3e library=cuda variant=v12 compute=8.6 driver=12.9 name="NVIDIA GeForce RTX 3080" total="10.0 GiB" available="8.9 GiB" ``` ### OS Windows ### GPU Nvidia ### CPU Intel ### Ollama version 0.9.5
GiteaMirror added the bug label 2026-04-12 19:31:51 -05:00
GiteaMirror commented 2026-04-12 19:31:51 -05:00
Author
Owner
Copy Link

@blakkd commented on GitHub (Jul 7, 2025):

time=2025-07-05T00:27:12.874-04:00 level=DEBUG source=amd_windows.go:34 msg="unable to load amdhip64_6.dll, please make sure to upgrade to the latest amd driver: The specified module could not be found.

Doesn't it simply come from here?

<!-- gh-comment-id:3045606082 --> @blakkd commented on GitHub (Jul 7, 2025): > `time=2025-07-05T00:27:12.874-04:00 level=DEBUG source=amd_windows.go:34 msg="unable to load amdhip64_6.dll, please make sure to upgrade to the latest amd driver: The specified module could not be found.` Doesn't it simply come from here?
GiteaMirror commented 2026-04-12 19:31:52 -05:00
Author
Owner
Copy Link

@Stogas commented on GitHub (Jul 7, 2025):

I don't think they're using any AMD hardware..

<!-- gh-comment-id:3046358788 --> @Stogas commented on GitHub (Jul 7, 2025): I don't think they're using any AMD hardware..
GiteaMirror commented 2026-04-12 19:31:52 -05:00
Author
Owner
Copy Link

@sguergachi commented on GitHub (Jul 8, 2025):

Running RTX3080 and an i7-8700k

<!-- gh-comment-id:3046972799 --> @sguergachi commented on GitHub (Jul 8, 2025): Running RTX3080 and an i7-8700k
GiteaMirror commented 2026-04-12 19:31:53 -05:00
Author
Owner
Copy Link

@blakkd commented on GitHub (Jul 8, 2025):

Oh yeah right sorry didn't pay attention too much attention to the screenshot!

<!-- gh-comment-id:3049076070 --> @blakkd commented on GitHub (Jul 8, 2025): Oh yeah right sorry didn't pay attention too much attention to the screenshot!
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#7455
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?