github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-16 21:25:46 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #8114] GPU not working on Windows. #67244

New Issue
Closed
opened 2026-05-04 09:43:02 -05:00 by GiteaMirror · 6 comments
GiteaMirror commented 2026-05-04 09:43:02 -05:00
Owner
Copy Link

Originally created by @odin-loki on GitHub (Dec 16, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/8114

What is the issue?

Hello, I am using the latest lama of today and am on a 10-year-old laptop. The logs say that Ollama is not detecting my GPU. I have a 4th Gen Intel i7 with 4 cores, 32 Gb of DDR3 Ram, a 4Gb 780M and am running Llama 3.3 Quantized 28 Gb. I'm pretty sure the framework is meant to buffer the AI on the GPU and slowly load it from memory. I don't think my GPU memory is the problem.

Here are my Logs:

App.Log:

time=2024-12-16T19:19:40.276+11:00 level=INFO source=logging.go:50 msg="ollama app started"
time=2024-12-16T19:19:40.276+11:00 level=INFO source=lifecycle.go:19 msg="app config" env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:C:\Users\odinl\.ollama\models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 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://*] OLLAMA_SCHED_SPREAD:false OLLAMA_TMPDIR: ROCR_VISIBLE_DEVICES:]"
time=2024-12-16T19:19:40.316+11:00 level=INFO source=server.go:182 msg="unable to connect to server"
time=2024-12-16T19:19:40.316+11:00 level=INFO source=server.go:141 msg="starting server..."
time=2024-12-16T19:19:40.898+11:00 level=INFO source=server.go:127 msg="started ollama server with pid 10904"
time=2024-12-16T19:19:40.898+11:00 level=INFO source=server.go:129 msg="ollama server logs C:\Users\odinl\AppData\Local\Ollama\server.log"

Server Log:

2024/12/16 19:19:41 routes.go:1195: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:C:\Users\odinl\.ollama\models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 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://*] OLLAMA_SCHED_SPREAD:false OLLAMA_TMPDIR: ROCR_VISIBLE_DEVICES:]"
time=2024-12-16T19:19:41.040+11:00 level=INFO source=images.go:753 msg="total blobs: 6"
time=2024-12-16T19:19:41.041+11:00 level=INFO source=images.go:760 msg="total unused blobs removed: 0"
time=2024-12-16T19:19:41.043+11:00 level=INFO source=routes.go:1246 msg="Listening on 127.0.0.1:11434 (version 0.5.1)"
time=2024-12-16T19:19:41.047+11:00 level=INFO source=common.go:49 msg="Dynamic LLM libraries" runners="[cpu_avx2 cuda_v11 cuda_v12 rocm cpu cpu_avx]"
time=2024-12-16T19:19:41.049+11:00 level=INFO source=gpu.go:221 msg="looking for compatible GPUs"
time=2024-12-16T19:19:41.049+11:00 level=INFO source=gpu_windows.go:167 msg=packages count=1
time=2024-12-16T19:19:41.049+11:00 level=INFO source=gpu_windows.go:214 msg="" package=0 cores=4 efficiency=0 threads=8
time=2024-12-16T19:19:41.073+11:00 level=INFO source=gpu.go:620 msg="Unable to load cudart library C:\Windows\system32\nvcuda.dll: symbol lookup for cuDeviceGetUuid failed: The specified procedure could not be found.\r\n"
time=2024-12-16T19:19:42.201+11:00 level=INFO source=gpu.go:386 msg="no compatible GPUs were discovered"
time=2024-12-16T19:19:42.201+11:00 level=INFO source=types.go:123 msg="inference compute" id=0 library=cpu variant=avx2 compute="" driver=0.0 name="" total="31.9 GiB" available="29.2 GiB"
[GIN] 2024/12/16 - 19:19:51 | 200 | 50.6µs | 127.0.0.1 | HEAD "/"
[GIN] 2024/12/16 - 19:19:51 | 200 | 99.5398ms | 127.0.0.1 | POST "/api/show"
time=2024-12-16T19:19:51.613+11:00 level=INFO source=server.go:105 msg="system memory" total="31.9 GiB" free="29.0 GiB" free_swap="33.8 GiB"
time=2024-12-16T19:19:51.615+11:00 level=INFO source=memory.go:356 msg="offload to cpu" layers.requested=-1 layers.model=81 layers.offload=0 layers.split="" memory.available="[29.0 GiB]" memory.gpu_overhead="0 B" memory.required.full="28.1 GiB" memory.required.partial="0 B" memory.required.kv="2.5 GiB" memory.required.allocations="[28.1 GiB]" memory.weights.total="25.9 GiB" memory.weights.repeating="25.1 GiB" memory.weights.nonrepeating="822.0 MiB" memory.graph.full="1.1 GiB" memory.graph.partial="1.1 GiB"
time=2024-12-16T19:19:51.623+11:00 level=INFO source=server.go:397 msg="starting llama server" cmd="C:\Users\odinl\AppData\Local\Programs\Ollama\lib\ollama\runners\cpu_avx2\ollama_llama_server.exe --model C:\Users\odinl\.ollama\models\blobs\sha256-35a6401f84b6c06d3d87140f6a437240cd02f65cc27216043911cda2bdde9137 --ctx-size 8192 --batch-size 512 --threads 4 --no-mmap --parallel 4 --port 49717"
time=2024-12-16T19:19:51.887+11:00 level=INFO source=sched.go:449 msg="loaded runners" count=1
time=2024-12-16T19:19:51.888+11:00 level=INFO source=server.go:576 msg="waiting for llama runner to start responding"
time=2024-12-16T19:19:51.889+11:00 level=INFO source=server.go:610 msg="waiting for server to become available" status="llm server error"
time=2024-12-16T19:19:51.917+11:00 level=INFO source=runner.go:941 msg="starting go runner"
time=2024-12-16T19:19:51.918+11:00 level=INFO source=runner.go:942 msg=system info="AVX = 1 | AVX_VNNI = 0 | AVX2 = 1 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | AVX512_BF16 = 0 | FMA = 1 | NEON = 0 | SVE = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | RISCV_VECT = 0 | WASM_SIMD = 0 | BLAS = 0 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 | LLAMAFILE = 1 | cgo(clang)" threads=4
time=2024-12-16T19:19:51.918+11:00 level=INFO source=.:0 msg="Server listening on 127.0.0.1:49717"
llama_model_loader: loaded meta data with 36 key-value pairs and 724 tensors from C:\Users\odinl.ollama\models\blobs\sha256-35a6401f84b6c06d3d87140f6a437240cd02f65cc27216043911cda2bdde9137 (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 = llama
llama_model_loader: - kv 1: general.type str = model
llama_model_loader: - kv 2: general.name str = Llama 3.1 70B Instruct 2024 12
llama_model_loader: - kv 3: general.version str = 2024-12
llama_model_loader: - kv 4: general.finetune str = Instruct
llama_model_loader: - kv 5: general.basename str = Llama-3.1
llama_model_loader: - kv 6: general.size_label str = 70B
llama_model_loader: - kv 7: general.license str = llama3.1
llama_model_loader: - kv 8: general.base_model.count u32 = 1
llama_model_loader: - kv 9: general.base_model.0.name str = Llama 3.1 70B
llama_model_loader: - kv 10: general.base_model.0.organization str = Meta Llama
llama_model_loader: - kv 11: general.base_model.0.repo_url str = https://huggingface.co/meta-llama/Lla...
llama_model_loader: - kv 12: general.tags arr[str,5] = ["facebook", "meta", "pytorch", "llam...
llama_model_loader: - kv 13: general.languages arr[str,7] = ["fr", "it", "pt", "hi", "es", "th", ...
llama_model_loader: - kv 14: llama.block_count u32 = 80
llama_model_loader: - kv 15: llama.context_length u32 = 131072
llama_model_loader: - kv 16: llama.embedding_length u32 = 8192
llama_model_loader: - kv 17: llama.feed_forward_length u32 = 28672
llama_model_loader: - kv 18: llama.attention.head_count u32 = 64
llama_model_loader: - kv 19: llama.attention.head_count_kv u32 = 8
llama_model_loader: - kv 20: llama.rope.freq_base f32 = 500000.000000
llama_model_loader: - kv 21: llama.attention.layer_norm_rms_epsilon f32 = 0.000010
llama_model_loader: - kv 22: llama.attention.key_length u32 = 128
llama_model_loader: - kv 23: llama.attention.value_length u32 = 128
llama_model_loader: - kv 24: general.file_type u32 = 10
llama_model_loader: - kv 25: llama.vocab_size u32 = 128256
llama_model_loader: - kv 26: llama.rope.dimension_count u32 = 128
llama_model_loader: - kv 27: tokenizer.ggml.model str = gpt2
llama_model_loader: - kv 28: tokenizer.ggml.pre str = llama-bpe
llama_model_loader: - kv 29: tokenizer.ggml.tokens arr[str,128256] = ["!", """, "#", "$", "%", "&", "'", ...
llama_model_loader: - kv 30: tokenizer.ggml.token_type arr[i32,128256] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv 31: tokenizer.ggml.merges arr[str,280147] = ["Ġ Ġ", "Ġ ĠĠĠ", "ĠĠ ĠĠ", "...
llama_model_loader: - kv 32: tokenizer.ggml.bos_token_id u32 = 128000
llama_model_loader: - kv 33: tokenizer.ggml.eos_token_id u32 = 128009
llama_model_loader: - kv 34: tokenizer.chat_template str = {{- bos_token }}\n{%- if custom_tools ...
llama_model_loader: - kv 35: general.quantization_version u32 = 2
llama_model_loader: - type f32: 162 tensors
llama_model_loader: - type q2_K: 321 tensors
llama_model_loader: - type q3_K: 160 tensors
llama_model_loader: - type q5_K: 80 tensors
llama_model_loader: - type q6_K: 1 tensors
time=2024-12-16T19:19:52.142+11:00 level=INFO source=server.go:610 msg="waiting for server to become available" status="llm server loading model"
llm_load_vocab: special tokens cache size = 256
llm_load_vocab: token to piece cache size = 0.7999 MB
llm_load_print_meta: format = GGUF V3 (latest)
llm_load_print_meta: arch = llama
llm_load_print_meta: vocab type = BPE
llm_load_print_meta: n_vocab = 128256
llm_load_print_meta: n_merges = 280147
llm_load_print_meta: vocab_only = 0
llm_load_print_meta: n_ctx_train = 131072
llm_load_print_meta: n_embd = 8192
llm_load_print_meta: n_layer = 80
llm_load_print_meta: n_head = 64
llm_load_print_meta: n_head_kv = 8
llm_load_print_meta: n_rot = 128
llm_load_print_meta: n_swa = 0
llm_load_print_meta: n_embd_head_k = 128
llm_load_print_meta: n_embd_head_v = 128
llm_load_print_meta: n_gqa = 8
llm_load_print_meta: n_embd_k_gqa = 1024
llm_load_print_meta: n_embd_v_gqa = 1024
llm_load_print_meta: f_norm_eps = 0.0e+00
llm_load_print_meta: f_norm_rms_eps = 1.0e-05
llm_load_print_meta: f_clamp_kqv = 0.0e+00
llm_load_print_meta: f_max_alibi_bias = 0.0e+00
llm_load_print_meta: f_logit_scale = 0.0e+00
llm_load_print_meta: n_ff = 28672
llm_load_print_meta: n_expert = 0
llm_load_print_meta: n_expert_used = 0
llm_load_print_meta: causal attn = 1
llm_load_print_meta: pooling type = 0
llm_load_print_meta: rope type = 0
llm_load_print_meta: rope scaling = linear
llm_load_print_meta: freq_base_train = 500000.0
llm_load_print_meta: freq_scale_train = 1
llm_load_print_meta: n_ctx_orig_yarn = 131072
llm_load_print_meta: rope_finetuned = unknown
llm_load_print_meta: ssm_d_conv = 0
llm_load_print_meta: ssm_d_inner = 0
llm_load_print_meta: ssm_d_state = 0
llm_load_print_meta: ssm_dt_rank = 0
llm_load_print_meta: ssm_dt_b_c_rms = 0
llm_load_print_meta: model type = 70B
llm_load_print_meta: model ftype = Q2_K - Medium
llm_load_print_meta: model params = 70.55 B
llm_load_print_meta: model size = 24.56 GiB (2.99 BPW)
llm_load_print_meta: general.name = Llama 3.1 70B Instruct 2024 12
llm_load_print_meta: BOS token = 128000 '<|begin_of_text|>'
llm_load_print_meta: EOS token = 128009 '<|eot_id|>'
llm_load_print_meta: LF token = 128 'Ä'
llm_load_print_meta: EOT token = 128009 '<|eot_id|>'
llm_load_print_meta: EOM token = 128008 '<|eom_id|>'
llm_load_print_meta: EOG token = 128008 '<|eom_id|>'
llm_load_print_meta: EOG token = 128009 '<|eot_id|>'
llm_load_print_meta: max token length = 256
llm_load_tensors: ggml ctx size = 0.34 MiB
llm_load_tensors: CPU buffer size = 25145.79 MiB
llama_new_context_with_model: n_ctx = 8192
llama_new_context_with_model: n_batch = 2048
llama_new_context_with_model: n_ubatch = 512
llama_new_context_with_model: flash_attn = 0
llama_new_context_with_model: freq_base = 500000.0
llama_new_context_with_model: freq_scale = 1
llama_kv_cache_init: CPU KV buffer size = 2560.00 MiB
llama_new_context_with_model: KV self size = 2560.00 MiB, K (f16): 1280.00 MiB, V (f16): 1280.00 MiB
llama_new_context_with_model: CPU output buffer size = 2.08 MiB
llama_new_context_with_model: CPU compute buffer size = 1104.01 MiB
llama_new_context_with_model: graph nodes = 2566
llama_new_context_with_model: graph splits = 1
time=2024-12-16T19:21:00.741+11:00 level=INFO source=server.go:615 msg="llama runner started in 68.85 seconds"
[GIN] 2024/12/16 - 19:22:47 | 200 | 2m56s | 127.0.0.1 | POST "/api/generate"

Note where it says no compatible GPU was found. Maybe my GPU is too old or the CUDA version isn't in Ollama

OS

Windows

GPU

Nvidia

CPU

Intel

Ollama version

0.5.1

Originally created by @odin-loki on GitHub (Dec 16, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/8114 ### What is the issue? Hello, I am using the latest lama of today and am on a 10-year-old laptop. The logs say that Ollama is not detecting my GPU. I have a 4th Gen Intel i7 with 4 cores, 32 Gb of DDR3 Ram, a 4Gb 780M and am running Llama 3.3 Quantized 28 Gb. I'm pretty sure the framework is meant to buffer the AI on the GPU and slowly load it from memory. I don't think my GPU memory is the problem. ### Here are my Logs: ### App.Log: time=2024-12-16T19:19:40.276+11:00 level=INFO source=logging.go:50 msg="ollama app started" time=2024-12-16T19:19:40.276+11:00 level=INFO source=lifecycle.go:19 msg="app config" env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:C:\\Users\\odinl\\.ollama\\models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 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://*] OLLAMA_SCHED_SPREAD:false OLLAMA_TMPDIR: ROCR_VISIBLE_DEVICES:]" time=2024-12-16T19:19:40.316+11:00 level=INFO source=server.go:182 msg="unable to connect to server" time=2024-12-16T19:19:40.316+11:00 level=INFO source=server.go:141 msg="starting server..." time=2024-12-16T19:19:40.898+11:00 level=INFO source=server.go:127 msg="started ollama server with pid 10904" time=2024-12-16T19:19:40.898+11:00 level=INFO source=server.go:129 msg="ollama server logs C:\\Users\\odinl\\AppData\\Local\\Ollama\\server.log" ### Server Log: 2024/12/16 19:19:41 routes.go:1195: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:C:\\Users\\odinl\\.ollama\\models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 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://*] OLLAMA_SCHED_SPREAD:false OLLAMA_TMPDIR: ROCR_VISIBLE_DEVICES:]" time=2024-12-16T19:19:41.040+11:00 level=INFO source=images.go:753 msg="total blobs: 6" time=2024-12-16T19:19:41.041+11:00 level=INFO source=images.go:760 msg="total unused blobs removed: 0" time=2024-12-16T19:19:41.043+11:00 level=INFO source=routes.go:1246 msg="Listening on 127.0.0.1:11434 (version 0.5.1)" time=2024-12-16T19:19:41.047+11:00 level=INFO source=common.go:49 msg="Dynamic LLM libraries" runners="[cpu_avx2 cuda_v11 cuda_v12 rocm cpu cpu_avx]" time=2024-12-16T19:19:41.049+11:00 level=INFO source=gpu.go:221 msg="looking for compatible GPUs" time=2024-12-16T19:19:41.049+11:00 level=INFO source=gpu_windows.go:167 msg=packages count=1 time=2024-12-16T19:19:41.049+11:00 level=INFO source=gpu_windows.go:214 msg="" package=0 cores=4 efficiency=0 threads=8 time=2024-12-16T19:19:41.073+11:00 level=INFO source=gpu.go:620 msg="Unable to load cudart library C:\\Windows\\system32\\nvcuda.dll: symbol lookup for cuDeviceGetUuid failed: The specified procedure could not be found.\r\n" time=2024-12-16T19:19:42.201+11:00 level=INFO source=gpu.go:386 msg="no compatible GPUs were discovered" time=2024-12-16T19:19:42.201+11:00 level=INFO source=types.go:123 msg="inference compute" id=0 library=cpu variant=avx2 compute="" driver=0.0 name="" total="31.9 GiB" available="29.2 GiB" [GIN] 2024/12/16 - 19:19:51 | 200 | 50.6µs | 127.0.0.1 | HEAD "/" [GIN] 2024/12/16 - 19:19:51 | 200 | 99.5398ms | 127.0.0.1 | POST "/api/show" time=2024-12-16T19:19:51.613+11:00 level=INFO source=server.go:105 msg="system memory" total="31.9 GiB" free="29.0 GiB" free_swap="33.8 GiB" time=2024-12-16T19:19:51.615+11:00 level=INFO source=memory.go:356 msg="offload to cpu" layers.requested=-1 layers.model=81 layers.offload=0 layers.split="" memory.available="[29.0 GiB]" memory.gpu_overhead="0 B" memory.required.full="28.1 GiB" memory.required.partial="0 B" memory.required.kv="2.5 GiB" memory.required.allocations="[28.1 GiB]" memory.weights.total="25.9 GiB" memory.weights.repeating="25.1 GiB" memory.weights.nonrepeating="822.0 MiB" memory.graph.full="1.1 GiB" memory.graph.partial="1.1 GiB" time=2024-12-16T19:19:51.623+11:00 level=INFO source=server.go:397 msg="starting llama server" cmd="C:\\Users\\odinl\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\runners\\cpu_avx2\\ollama_llama_server.exe --model C:\\Users\\odinl\\.ollama\\models\\blobs\\sha256-35a6401f84b6c06d3d87140f6a437240cd02f65cc27216043911cda2bdde9137 --ctx-size 8192 --batch-size 512 --threads 4 --no-mmap --parallel 4 --port 49717" time=2024-12-16T19:19:51.887+11:00 level=INFO source=sched.go:449 msg="loaded runners" count=1 time=2024-12-16T19:19:51.888+11:00 level=INFO source=server.go:576 msg="waiting for llama runner to start responding" time=2024-12-16T19:19:51.889+11:00 level=INFO source=server.go:610 msg="waiting for server to become available" status="llm server error" time=2024-12-16T19:19:51.917+11:00 level=INFO source=runner.go:941 msg="starting go runner" time=2024-12-16T19:19:51.918+11:00 level=INFO source=runner.go:942 msg=system info="AVX = 1 | AVX_VNNI = 0 | AVX2 = 1 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | AVX512_BF16 = 0 | FMA = 1 | NEON = 0 | SVE = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | RISCV_VECT = 0 | WASM_SIMD = 0 | BLAS = 0 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 | LLAMAFILE = 1 | cgo(clang)" threads=4 time=2024-12-16T19:19:51.918+11:00 level=INFO source=.:0 msg="Server listening on 127.0.0.1:49717" llama_model_loader: loaded meta data with 36 key-value pairs and 724 tensors from C:\Users\odinl\.ollama\models\blobs\sha256-35a6401f84b6c06d3d87140f6a437240cd02f65cc27216043911cda2bdde9137 (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 = llama llama_model_loader: - kv 1: general.type str = model llama_model_loader: - kv 2: general.name str = Llama 3.1 70B Instruct 2024 12 llama_model_loader: - kv 3: general.version str = 2024-12 llama_model_loader: - kv 4: general.finetune str = Instruct llama_model_loader: - kv 5: general.basename str = Llama-3.1 llama_model_loader: - kv 6: general.size_label str = 70B llama_model_loader: - kv 7: general.license str = llama3.1 llama_model_loader: - kv 8: general.base_model.count u32 = 1 llama_model_loader: - kv 9: general.base_model.0.name str = Llama 3.1 70B llama_model_loader: - kv 10: general.base_model.0.organization str = Meta Llama llama_model_loader: - kv 11: general.base_model.0.repo_url str = https://huggingface.co/meta-llama/Lla... llama_model_loader: - kv 12: general.tags arr[str,5] = ["facebook", "meta", "pytorch", "llam... llama_model_loader: - kv 13: general.languages arr[str,7] = ["fr", "it", "pt", "hi", "es", "th", ... llama_model_loader: - kv 14: llama.block_count u32 = 80 llama_model_loader: - kv 15: llama.context_length u32 = 131072 llama_model_loader: - kv 16: llama.embedding_length u32 = 8192 llama_model_loader: - kv 17: llama.feed_forward_length u32 = 28672 llama_model_loader: - kv 18: llama.attention.head_count u32 = 64 llama_model_loader: - kv 19: llama.attention.head_count_kv u32 = 8 llama_model_loader: - kv 20: llama.rope.freq_base f32 = 500000.000000 llama_model_loader: - kv 21: llama.attention.layer_norm_rms_epsilon f32 = 0.000010 llama_model_loader: - kv 22: llama.attention.key_length u32 = 128 llama_model_loader: - kv 23: llama.attention.value_length u32 = 128 llama_model_loader: - kv 24: general.file_type u32 = 10 llama_model_loader: - kv 25: llama.vocab_size u32 = 128256 llama_model_loader: - kv 26: llama.rope.dimension_count u32 = 128 llama_model_loader: - kv 27: tokenizer.ggml.model str = gpt2 llama_model_loader: - kv 28: tokenizer.ggml.pre str = llama-bpe llama_model_loader: - kv 29: tokenizer.ggml.tokens arr[str,128256] = ["!", "\"", "#", "$", "%", "&", "'", ... llama_model_loader: - kv 30: tokenizer.ggml.token_type arr[i32,128256] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 31: tokenizer.ggml.merges arr[str,280147] = ["Ġ Ġ", "Ġ ĠĠĠ", "ĠĠ ĠĠ", "... llama_model_loader: - kv 32: tokenizer.ggml.bos_token_id u32 = 128000 llama_model_loader: - kv 33: tokenizer.ggml.eos_token_id u32 = 128009 llama_model_loader: - kv 34: tokenizer.chat_template str = {{- bos_token }}\n{%- if custom_tools ... llama_model_loader: - kv 35: general.quantization_version u32 = 2 llama_model_loader: - type f32: 162 tensors llama_model_loader: - type q2_K: 321 tensors llama_model_loader: - type q3_K: 160 tensors llama_model_loader: - type q5_K: 80 tensors llama_model_loader: - type q6_K: 1 tensors time=2024-12-16T19:19:52.142+11:00 level=INFO source=server.go:610 msg="waiting for server to become available" status="llm server loading model" llm_load_vocab: special tokens cache size = 256 llm_load_vocab: token to piece cache size = 0.7999 MB llm_load_print_meta: format = GGUF V3 (latest) llm_load_print_meta: arch = llama llm_load_print_meta: vocab type = BPE llm_load_print_meta: n_vocab = 128256 llm_load_print_meta: n_merges = 280147 llm_load_print_meta: vocab_only = 0 llm_load_print_meta: n_ctx_train = 131072 llm_load_print_meta: n_embd = 8192 llm_load_print_meta: n_layer = 80 llm_load_print_meta: n_head = 64 llm_load_print_meta: n_head_kv = 8 llm_load_print_meta: n_rot = 128 llm_load_print_meta: n_swa = 0 llm_load_print_meta: n_embd_head_k = 128 llm_load_print_meta: n_embd_head_v = 128 llm_load_print_meta: n_gqa = 8 llm_load_print_meta: n_embd_k_gqa = 1024 llm_load_print_meta: n_embd_v_gqa = 1024 llm_load_print_meta: f_norm_eps = 0.0e+00 llm_load_print_meta: f_norm_rms_eps = 1.0e-05 llm_load_print_meta: f_clamp_kqv = 0.0e+00 llm_load_print_meta: f_max_alibi_bias = 0.0e+00 llm_load_print_meta: f_logit_scale = 0.0e+00 llm_load_print_meta: n_ff = 28672 llm_load_print_meta: n_expert = 0 llm_load_print_meta: n_expert_used = 0 llm_load_print_meta: causal attn = 1 llm_load_print_meta: pooling type = 0 llm_load_print_meta: rope type = 0 llm_load_print_meta: rope scaling = linear llm_load_print_meta: freq_base_train = 500000.0 llm_load_print_meta: freq_scale_train = 1 llm_load_print_meta: n_ctx_orig_yarn = 131072 llm_load_print_meta: rope_finetuned = unknown llm_load_print_meta: ssm_d_conv = 0 llm_load_print_meta: ssm_d_inner = 0 llm_load_print_meta: ssm_d_state = 0 llm_load_print_meta: ssm_dt_rank = 0 llm_load_print_meta: ssm_dt_b_c_rms = 0 llm_load_print_meta: model type = 70B llm_load_print_meta: model ftype = Q2_K - Medium llm_load_print_meta: model params = 70.55 B llm_load_print_meta: model size = 24.56 GiB (2.99 BPW) llm_load_print_meta: general.name = Llama 3.1 70B Instruct 2024 12 llm_load_print_meta: BOS token = 128000 '<|begin_of_text|>' llm_load_print_meta: EOS token = 128009 '<|eot_id|>' llm_load_print_meta: LF token = 128 'Ä' llm_load_print_meta: EOT token = 128009 '<|eot_id|>' llm_load_print_meta: EOM token = 128008 '<|eom_id|>' llm_load_print_meta: EOG token = 128008 '<|eom_id|>' llm_load_print_meta: EOG token = 128009 '<|eot_id|>' llm_load_print_meta: max token length = 256 llm_load_tensors: ggml ctx size = 0.34 MiB llm_load_tensors: CPU buffer size = 25145.79 MiB llama_new_context_with_model: n_ctx = 8192 llama_new_context_with_model: n_batch = 2048 llama_new_context_with_model: n_ubatch = 512 llama_new_context_with_model: flash_attn = 0 llama_new_context_with_model: freq_base = 500000.0 llama_new_context_with_model: freq_scale = 1 llama_kv_cache_init: CPU KV buffer size = 2560.00 MiB llama_new_context_with_model: KV self size = 2560.00 MiB, K (f16): 1280.00 MiB, V (f16): 1280.00 MiB llama_new_context_with_model: CPU output buffer size = 2.08 MiB llama_new_context_with_model: CPU compute buffer size = 1104.01 MiB llama_new_context_with_model: graph nodes = 2566 llama_new_context_with_model: graph splits = 1 time=2024-12-16T19:21:00.741+11:00 level=INFO source=server.go:615 msg="llama runner started in 68.85 seconds" [GIN] 2024/12/16 - 19:22:47 | 200 | 2m56s | 127.0.0.1 | POST "/api/generate" Note where it says no compatible GPU was found. Maybe my GPU is too old or the CUDA version isn't in Ollama ### OS Windows ### GPU Nvidia ### CPU Intel ### Ollama version 0.5.1
GiteaMirror added the nvidiaquestion labels 2026-05-04 09:43:02 -05:00
GiteaMirror commented 2026-05-04 09:43:09 -05:00
Author
Owner
Copy Link

@pugafran commented on GitHub (Dec 16, 2024):

You have an old AMD graphics card, AMD graphics cards do not use CUDA, which is a platform belonging to NVIDIA. AMD if I remember correctly uses ROCm, and Ollama only supports a few graphics cards:

image

Check this link: https://ollama.com/blog/amd-preview

<!-- gh-comment-id:2545401735 --> @pugafran commented on GitHub (Dec 16, 2024): You have an old AMD graphics card, AMD graphics cards do not use CUDA, which is a platform belonging to NVIDIA. AMD if I remember correctly uses ROCm, and Ollama only supports a few graphics cards: ![image](https://github.com/user-attachments/assets/dfd3f202-1197-48d5-aaa3-db35b1a6b21a) Check this link: https://ollama.com/blog/amd-preview
GiteaMirror commented 2026-05-04 09:43:10 -05:00
Author
Owner
Copy Link

@odin-loki commented on GitHub (Dec 16, 2024):

No. I have an old Nvidia card. It uses CUDA. Its a Nvidia Geforce 780M. Uve had it for 10 years.

From: Francisco Puga Lojo @.>
Sent: Monday, December 16, 2024 10:45:14 PM
To: ollama/ollama @.>
Cc: Odin @.>; Author @.>
Subject: Re: [ollama/ollama] GPU not working on Windows. (Issue #8114)

You have an old AMD graphics card, AMD graphics cards do not use CUDA, which is a platform belonging to NVIDIA. AMD if I remember correctly uses ROCm, and Ollama only supports a few graphics cards:

image.png (view on web)https://github.com/user-attachments/assets/dfd3f202-1197-48d5-aaa3-db35b1a6b21a

Check this link: https://ollama.com/blog/amd-preview

—
Reply to this email directly, view it on GitHubhttps://github.com/ollama/ollama/issues/8114#issuecomment-2545401735, or unsubscribehttps://github.com/notifications/unsubscribe-auth/AGJ7D5JQ2USKKBJ5X7UOLQD2F24MVAVCNFSM6AAAAABTVTTUPKVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDKNBVGQYDCNZTGU.
You are receiving this because you authored the thread.Message ID: @.***>

<!-- gh-comment-id:2546355230 --> @odin-loki commented on GitHub (Dec 16, 2024): No. I have an old Nvidia card. It uses CUDA. Its a Nvidia Geforce 780M. Uve had it for 10 years. ________________________________ From: Francisco Puga Lojo ***@***.***> Sent: Monday, December 16, 2024 10:45:14 PM To: ollama/ollama ***@***.***> Cc: Odin ***@***.***>; Author ***@***.***> Subject: Re: [ollama/ollama] GPU not working on Windows. (Issue #8114) You have an old AMD graphics card, AMD graphics cards do not use CUDA, which is a platform belonging to NVIDIA. AMD if I remember correctly uses ROCm, and Ollama only supports a few graphics cards: image.png (view on web)<https://github.com/user-attachments/assets/dfd3f202-1197-48d5-aaa3-db35b1a6b21a> Check this link: https://ollama.com/blog/amd-preview — Reply to this email directly, view it on GitHub<https://github.com/ollama/ollama/issues/8114#issuecomment-2545401735>, or unsubscribe<https://github.com/notifications/unsubscribe-auth/AGJ7D5JQ2USKKBJ5X7UOLQD2F24MVAVCNFSM6AAAAABTVTTUPKVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDKNBVGQYDCNZTGU>. You are receiving this because you authored the thread.Message ID: ***@***.***>
GiteaMirror commented 2026-05-04 09:43:12 -05:00
Author
Owner
Copy Link

@odin-loki commented on GitHub (Dec 16, 2024):

It doesnt support it anyway. I checked.

From: Francisco Puga Lojo @.>
Sent: Monday, December 16, 2024 10:45:14 PM
To: ollama/ollama @.>
Cc: Odin @.>; Author @.>
Subject: Re: [ollama/ollama] GPU not working on Windows. (Issue #8114)

You have an old AMD graphics card, AMD graphics cards do not use CUDA, which is a platform belonging to NVIDIA. AMD if I remember correctly uses ROCm, and Ollama only supports a few graphics cards:

image.png (view on web)https://github.com/user-attachments/assets/dfd3f202-1197-48d5-aaa3-db35b1a6b21a

Check this link: https://ollama.com/blog/amd-preview

—
Reply to this email directly, view it on GitHubhttps://github.com/ollama/ollama/issues/8114#issuecomment-2545401735, or unsubscribehttps://github.com/notifications/unsubscribe-auth/AGJ7D5JQ2USKKBJ5X7UOLQD2F24MVAVCNFSM6AAAAABTVTTUPKVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDKNBVGQYDCNZTGU.
You are receiving this because you authored the thread.Message ID: @.***>

<!-- gh-comment-id:2546361436 --> @odin-loki commented on GitHub (Dec 16, 2024): It doesnt support it anyway. I checked. ________________________________ From: Francisco Puga Lojo ***@***.***> Sent: Monday, December 16, 2024 10:45:14 PM To: ollama/ollama ***@***.***> Cc: Odin ***@***.***>; Author ***@***.***> Subject: Re: [ollama/ollama] GPU not working on Windows. (Issue #8114) You have an old AMD graphics card, AMD graphics cards do not use CUDA, which is a platform belonging to NVIDIA. AMD if I remember correctly uses ROCm, and Ollama only supports a few graphics cards: image.png (view on web)<https://github.com/user-attachments/assets/dfd3f202-1197-48d5-aaa3-db35b1a6b21a> Check this link: https://ollama.com/blog/amd-preview — Reply to this email directly, view it on GitHub<https://github.com/ollama/ollama/issues/8114#issuecomment-2545401735>, or unsubscribe<https://github.com/notifications/unsubscribe-auth/AGJ7D5JQ2USKKBJ5X7UOLQD2F24MVAVCNFSM6AAAAABTVTTUPKVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDKNBVGQYDCNZTGU>. You are receiving this because you authored the thread.Message ID: ***@***.***>
GiteaMirror commented 2026-05-04 09:43:14 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Dec 16, 2024):

Geforce 780M has compute capacity 3.0 and is not supported.

<!-- gh-comment-id:2546386429 --> @rick-github commented on GitHub (Dec 16, 2024): Geforce 780M has compute capacity 3.0 and is not supported.
GiteaMirror commented 2026-05-04 09:43:14 -05:00
Author
Owner
Copy Link

@odin-loki commented on GitHub (Dec 16, 2024):

Thanks mate. Looks like I finally have to upgrade PC.

From: frob @.>
Sent: Tuesday, December 17, 2024 5:49:22 AM
To: ollama/ollama @.>
Cc: Odin @.>; Author @.>
Subject: Re: [ollama/ollama] GPU not working on Windows. (Issue #8114)

Geforce 780M has compute capacity 3.0 and is not supported.

—
Reply to this email directly, view it on GitHubhttps://github.com/ollama/ollama/issues/8114#issuecomment-2546386429, or unsubscribehttps://github.com/notifications/unsubscribe-auth/AGJ7D5OX3UUBP3UZ7VH5FVT2F4ODFAVCNFSM6AAAAABTVTTUPKVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDKNBWGM4DMNBSHE.
You are receiving this because you authored the thread.Message ID: @.***>

<!-- gh-comment-id:2546435622 --> @odin-loki commented on GitHub (Dec 16, 2024): Thanks mate. Looks like I finally have to upgrade PC. ________________________________ From: frob ***@***.***> Sent: Tuesday, December 17, 2024 5:49:22 AM To: ollama/ollama ***@***.***> Cc: Odin ***@***.***>; Author ***@***.***> Subject: Re: [ollama/ollama] GPU not working on Windows. (Issue #8114) Geforce 780M has compute capacity 3.0 and is not supported. — Reply to this email directly, view it on GitHub<https://github.com/ollama/ollama/issues/8114#issuecomment-2546386429>, or unsubscribe<https://github.com/notifications/unsubscribe-auth/AGJ7D5OX3UUBP3UZ7VH5FVT2F4ODFAVCNFSM6AAAAABTVTTUPKVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDKNBWGM4DMNBSHE>. You are receiving this because you authored the thread.Message ID: ***@***.***>
GiteaMirror commented 2026-05-04 09:43:14 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Dec 16, 2024):

For Compute Capability 3.5 and 3.7 you can build from source, but I don't believe 3.0 will be viable unfortunately.

https://github.com/ollama/ollama/blob/main/docs/development.md#older-linux-cuda-nvidia

<!-- gh-comment-id:2547147307 --> @dhiltgen commented on GitHub (Dec 16, 2024): For Compute Capability 3.5 and 3.7 you can build from source, but I don't believe 3.0 will be viable unfortunately. https://github.com/ollama/ollama/blob/main/docs/development.md#older-linux-cuda-nvidia
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 nvidia question
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#67244
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?