github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 08:02:14 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #13153] Vulkan #8699

New Issue
Open
opened 2026-04-12 21:28:21 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-12 21:28:21 -05:00
Owner
Copy Link

Originally created by @Swagatade on GitHub (Nov 19, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/13153

What is the issue?

intel ultra processor gpt-oss-safeguard very slow using Vulkan support. But only cpu performence is perfect.

Relevant log output

C:\Users\swaga_nsppntr>set OLLAMA_VULKAN=1

C:\Users\swaga_nsppntr>ollama serve
time=2025-11-19T11:14:58.021+05:30 level=INFO source=routes.go:1544 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GGML_VK_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:4096 OLLAMA_DEBUG:INFO OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 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\\swaga_nsppntr\\.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_REMOTES:[ollama.com] OLLAMA_SCHED_SPREAD:false OLLAMA_VULKAN:true ROCR_VISIBLE_DEVICES:]"
time=2025-11-19T11:14:58.272+05:30 level=INFO source=images.go:522 msg="total blobs: 74"
time=2025-11-19T11:14:58.277+05:30 level=INFO source=images.go:529 msg="total unused blobs removed: 0"
time=2025-11-19T11:14:58.283+05:30 level=INFO source=routes.go:1597 msg="Listening on 127.0.0.1:11434 (version 0.12.11)"
time=2025-11-19T11:14:58.285+05:30 level=INFO source=runner.go:67 msg="discovering available GPUs..."
time=2025-11-19T11:14:58.299+05:30 level=INFO source=server.go:392 msg="starting runner" cmd="C:\\Users\\swaga_nsppntr\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 51942"
time=2025-11-19T11:14:59.184+05:30 level=INFO source=server.go:392 msg="starting runner" cmd="C:\\Users\\swaga_nsppntr\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 51954"
time=2025-11-19T11:14:59.964+05:30 level=INFO source=server.go:392 msg="starting runner" cmd="C:\\Users\\swaga_nsppntr\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 51961"
time=2025-11-19T11:15:00.292+05:30 level=INFO source=server.go:392 msg="starting runner" cmd="C:\\Users\\swaga_nsppntr\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 51966"
time=2025-11-19T11:15:00.877+05:30 level=INFO source=types.go:42 msg="inference compute" id=8680a064-0400-0000-0002-000000000000 filter_id="" library=Vulkan compute=0.0 name=Vulkan0 description="Intel(R) Arc(TM) 130V GPU (16GB)" libdirs=ollama,vulkan driver=0.0 pci_id="" type=iGPU total="27.6 GiB" available="26.8 GiB"
[GIN] 2025/11/19 - 11:15:40 | 200 |      2.1217ms |       127.0.0.1 | GET      "/api/version"
[GIN] 2025/11/19 - 11:15:41 | 200 |     371.946ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2025/11/19 - 11:15:41 | 200 |    335.6007ms |       127.0.0.1 | POST     "/api/show"
[GIN] 2025/11/19 - 11:15:43 | 200 |     34.5837ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2025/11/19 - 11:15:44 | 200 |    155.6211ms |       127.0.0.1 | POST     "/api/show"
[GIN] 2025/11/19 - 11:15:44 | 200 |    116.4347ms |       127.0.0.1 | POST     "/api/show"
time=2025-11-19T11:15:44.389+05:30 level=INFO source=server.go:392 msg="starting runner" cmd="C:\\Users\\swaga_nsppntr\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 57220"
time=2025-11-19T11:15:45.033+05:30 level=INFO source=cpu_windows.go:148 msg=packages count=1
time=2025-11-19T11:15:45.033+05:30 level=INFO source=cpu_windows.go:164 msg="efficiency cores detected" maxEfficiencyClass=1
time=2025-11-19T11:15:45.034+05:30 level=INFO source=cpu_windows.go:195 msg="" package=0 cores=8 efficiency=4 threads=8
time=2025-11-19T11:15:45.191+05:30 level=INFO source=server.go:209 msg="enabling flash attention"
time=2025-11-19T11:15:45.194+05:30 level=INFO source=server.go:392 msg="starting runner" cmd="C:\\Users\\swaga_nsppntr\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --model C:\\Users\\swaga_nsppntr\\.ollama\\models\\blobs\\sha256-c4016c9e54d0a9218b5911790579e58284a9ed57c48b7e87607125c6307f9da1 --port 57231"
time=2025-11-19T11:15:45.198+05:30 level=INFO source=sched.go:443 msg="system memory" total="31.5 GiB" free="17.0 GiB" free_swap="31.9 GiB"
time=2025-11-19T11:15:45.198+05:30 level=INFO source=sched.go:450 msg="gpu memory" id=8680a064-0400-0000-0002-000000000000 library=Vulkan available="26.1 GiB" free="26.6 GiB" minimum="457.0 MiB" overhead="0 B"
time=2025-11-19T11:15:45.198+05:30 level=INFO source=server.go:702 msg="loading model" "model layers"=25 requested=-1
time=2025-11-19T11:15:45.258+05:30 level=INFO source=runner.go:1398 msg="starting ollama engine"
time=2025-11-19T11:15:45.260+05:30 level=INFO source=runner.go:1433 msg="Server listening on 127.0.0.1:57231"
time=2025-11-19T11:15:45.267+05:30 level=INFO source=runner.go:1271 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:true KvSize:8192 KvCacheType: NumThreads:4 GPULayers:25[ID:8680a064-0400-0000-0002-000000000000 Layers:25(0..24)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2025-11-19T11:15:45.322+05:30 level=INFO source=ggml.go:136 msg="" architecture=gptoss file_type=MXFP4 name="" description="" num_tensors=459 num_key_values=32
load_backend: loaded CPU backend from C:\Users\swaga_nsppntr\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-alderlake.dll
ggml_vulkan: Found 1 Vulkan devices:
ggml_vulkan: 0 = Intel(R) Arc(TM) 130V GPU (16GB) (Intel Corporation) | uma: 1 | fp16: 1 | bf16: 0 | warp size: 32 | shared memory: 32768 | int dot: 1 | matrix cores: KHR_coopmat
load_backend: loaded Vulkan backend from C:\Users\swaga_nsppntr\AppData\Local\Programs\Ollama\lib\ollama\vulkan\ggml-vulkan.dll
time=2025-11-19T11:15:45.427+05:30 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 compiler=cgo(clang)
ggml_backend_vk_get_device_memory called: uuid 8680a064-0400-0000-0002-000000000000
ggml_backend_vk_get_device_memory called: luid 0x000000000000ff6b
ggml_dxgi_pdh_init called
DXGI + PDH Initialized. Getting GPU free memory info
[DXGI] Adapter Description: Intel(R) Arc(TM) 130V GPU (16GB), LUID: 0x000000000000FF6B, Dedicated: 0.12 GB, Shared: 27.45 GB
[DXGI] Adapter Description: Microsoft Basic Render Driver, LUID: 0x000000000001038E, Dedicated: 0.00 GB, Shared: 27.45 GB
Integrated GPU (Intel(R) Arc(TM) 130V GPU (16GB)) with LUID 0x000000000000ff6b detected. Shared Total: 29470189240.00 bytes (27.45 GB), Shared Usage: 1070800896.00 bytes (1.00 GB), Dedicated Total: 134217728.00 bytes (0.12 GB), Dedicated Usage: 0.00 bytes (0.00 GB)
ggml_backend_vk_get_device_memory utilizing DXGI + PDH memory reporting free: 28533606072 total: 29604406968
time=2025-11-19T11:15:45.809+05:30 level=INFO source=runner.go:1271 msg=load request="{Operation:alloc LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:true KvSize:8192 KvCacheType: NumThreads:4 GPULayers:25[ID:8680a064-0400-0000-0002-000000000000 Layers:25(0..24)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
ggml_backend_vk_get_device_memory called: uuid 8680a064-0400-0000-0002-000000000000
ggml_backend_vk_get_device_memory called: luid 0x000000000000ff6b
ggml_dxgi_pdh_init called
DXGI + PDH Initialized. Getting GPU free memory info
[DXGI] Adapter Description: Intel(R) Arc(TM) 130V GPU (16GB), LUID: 0x000000000000FF6B, Dedicated: 0.12 GB, Shared: 27.45 GB
[DXGI] Adapter Description: Microsoft Basic Render Driver, LUID: 0x000000000001038E, Dedicated: 0.00 GB, Shared: 27.45 GB
Integrated GPU (Intel(R) Arc(TM) 130V GPU (16GB)) with LUID 0x000000000000ff6b detected. Shared Total: 29470189240.00 bytes (27.45 GB), Shared Usage: 1070800896.00 bytes (1.00 GB), Dedicated Total: 134217728.00 bytes (0.12 GB), Dedicated Usage: 0.00 bytes (0.00 GB)
ggml_backend_vk_get_device_memory utilizing DXGI + PDH memory reporting free: 28533606072 total: 29604406968
time=2025-11-19T11:15:51.463+05:30 level=INFO source=runner.go:1271 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:true KvSize:8192 KvCacheType: NumThreads:4 GPULayers:25[ID:8680a064-0400-0000-0002-000000000000 Layers:25(0..24)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2025-11-19T11:15:51.463+05:30 level=INFO source=ggml.go:482 msg="offloading 24 repeating layers to GPU"
time=2025-11-19T11:15:51.463+05:30 level=INFO source=ggml.go:489 msg="offloading output layer to GPU"
time=2025-11-19T11:15:51.463+05:30 level=INFO source=ggml.go:494 msg="offloaded 25/25 layers to GPU"
time=2025-11-19T11:15:51.465+05:30 level=INFO source=device.go:240 msg="model weights" device=Vulkan0 size="11.8 GiB"
time=2025-11-19T11:15:51.465+05:30 level=INFO source=device.go:245 msg="model weights" device=CPU size="1.1 GiB"
time=2025-11-19T11:15:51.465+05:30 level=INFO source=device.go:251 msg="kv cache" device=Vulkan0 size="300.0 MiB"
time=2025-11-19T11:15:51.465+05:30 level=INFO source=device.go:262 msg="compute graph" device=Vulkan0 size="110.6 MiB"
time=2025-11-19T11:15:51.467+05:30 level=INFO source=device.go:267 msg="compute graph" device=CPU size="5.6 MiB"
time=2025-11-19T11:15:51.468+05:30 level=INFO source=device.go:272 msg="total memory" size="13.2 GiB"
time=2025-11-19T11:15:51.468+05:30 level=INFO source=sched.go:517 msg="loaded runners" count=1
time=2025-11-19T11:15:51.468+05:30 level=INFO source=server.go:1294 msg="waiting for llama runner to start responding"
time=2025-11-19T11:15:51.469+05:30 level=INFO source=server.go:1328 msg="waiting for server to become available" status="llm server loading model"

OS

Windows

GPU

Intel

CPU

Intel

Ollama version

v0.12.11

Originally created by @Swagatade on GitHub (Nov 19, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/13153 ### What is the issue? intel ultra processor gpt-oss-safeguard very slow using Vulkan support. But only cpu performence is perfect. ### Relevant log output ```shell C:\Users\swaga_nsppntr>set OLLAMA_VULKAN=1 C:\Users\swaga_nsppntr>ollama serve time=2025-11-19T11:14:58.021+05:30 level=INFO source=routes.go:1544 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GGML_VK_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:4096 OLLAMA_DEBUG:INFO OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 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\\swaga_nsppntr\\.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_REMOTES:[ollama.com] OLLAMA_SCHED_SPREAD:false OLLAMA_VULKAN:true ROCR_VISIBLE_DEVICES:]" time=2025-11-19T11:14:58.272+05:30 level=INFO source=images.go:522 msg="total blobs: 74" time=2025-11-19T11:14:58.277+05:30 level=INFO source=images.go:529 msg="total unused blobs removed: 0" time=2025-11-19T11:14:58.283+05:30 level=INFO source=routes.go:1597 msg="Listening on 127.0.0.1:11434 (version 0.12.11)" time=2025-11-19T11:14:58.285+05:30 level=INFO source=runner.go:67 msg="discovering available GPUs..." time=2025-11-19T11:14:58.299+05:30 level=INFO source=server.go:392 msg="starting runner" cmd="C:\\Users\\swaga_nsppntr\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 51942" time=2025-11-19T11:14:59.184+05:30 level=INFO source=server.go:392 msg="starting runner" cmd="C:\\Users\\swaga_nsppntr\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 51954" time=2025-11-19T11:14:59.964+05:30 level=INFO source=server.go:392 msg="starting runner" cmd="C:\\Users\\swaga_nsppntr\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 51961" time=2025-11-19T11:15:00.292+05:30 level=INFO source=server.go:392 msg="starting runner" cmd="C:\\Users\\swaga_nsppntr\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 51966" time=2025-11-19T11:15:00.877+05:30 level=INFO source=types.go:42 msg="inference compute" id=8680a064-0400-0000-0002-000000000000 filter_id="" library=Vulkan compute=0.0 name=Vulkan0 description="Intel(R) Arc(TM) 130V GPU (16GB)" libdirs=ollama,vulkan driver=0.0 pci_id="" type=iGPU total="27.6 GiB" available="26.8 GiB" [GIN] 2025/11/19 - 11:15:40 | 200 | 2.1217ms | 127.0.0.1 | GET "/api/version" [GIN] 2025/11/19 - 11:15:41 | 200 | 371.946ms | 127.0.0.1 | GET "/api/tags" [GIN] 2025/11/19 - 11:15:41 | 200 | 335.6007ms | 127.0.0.1 | POST "/api/show" [GIN] 2025/11/19 - 11:15:43 | 200 | 34.5837ms | 127.0.0.1 | GET "/api/tags" [GIN] 2025/11/19 - 11:15:44 | 200 | 155.6211ms | 127.0.0.1 | POST "/api/show" [GIN] 2025/11/19 - 11:15:44 | 200 | 116.4347ms | 127.0.0.1 | POST "/api/show" time=2025-11-19T11:15:44.389+05:30 level=INFO source=server.go:392 msg="starting runner" cmd="C:\\Users\\swaga_nsppntr\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 57220" time=2025-11-19T11:15:45.033+05:30 level=INFO source=cpu_windows.go:148 msg=packages count=1 time=2025-11-19T11:15:45.033+05:30 level=INFO source=cpu_windows.go:164 msg="efficiency cores detected" maxEfficiencyClass=1 time=2025-11-19T11:15:45.034+05:30 level=INFO source=cpu_windows.go:195 msg="" package=0 cores=8 efficiency=4 threads=8 time=2025-11-19T11:15:45.191+05:30 level=INFO source=server.go:209 msg="enabling flash attention" time=2025-11-19T11:15:45.194+05:30 level=INFO source=server.go:392 msg="starting runner" cmd="C:\\Users\\swaga_nsppntr\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --model C:\\Users\\swaga_nsppntr\\.ollama\\models\\blobs\\sha256-c4016c9e54d0a9218b5911790579e58284a9ed57c48b7e87607125c6307f9da1 --port 57231" time=2025-11-19T11:15:45.198+05:30 level=INFO source=sched.go:443 msg="system memory" total="31.5 GiB" free="17.0 GiB" free_swap="31.9 GiB" time=2025-11-19T11:15:45.198+05:30 level=INFO source=sched.go:450 msg="gpu memory" id=8680a064-0400-0000-0002-000000000000 library=Vulkan available="26.1 GiB" free="26.6 GiB" minimum="457.0 MiB" overhead="0 B" time=2025-11-19T11:15:45.198+05:30 level=INFO source=server.go:702 msg="loading model" "model layers"=25 requested=-1 time=2025-11-19T11:15:45.258+05:30 level=INFO source=runner.go:1398 msg="starting ollama engine" time=2025-11-19T11:15:45.260+05:30 level=INFO source=runner.go:1433 msg="Server listening on 127.0.0.1:57231" time=2025-11-19T11:15:45.267+05:30 level=INFO source=runner.go:1271 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:true KvSize:8192 KvCacheType: NumThreads:4 GPULayers:25[ID:8680a064-0400-0000-0002-000000000000 Layers:25(0..24)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2025-11-19T11:15:45.322+05:30 level=INFO source=ggml.go:136 msg="" architecture=gptoss file_type=MXFP4 name="" description="" num_tensors=459 num_key_values=32 load_backend: loaded CPU backend from C:\Users\swaga_nsppntr\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-alderlake.dll ggml_vulkan: Found 1 Vulkan devices: ggml_vulkan: 0 = Intel(R) Arc(TM) 130V GPU (16GB) (Intel Corporation) | uma: 1 | fp16: 1 | bf16: 0 | warp size: 32 | shared memory: 32768 | int dot: 1 | matrix cores: KHR_coopmat load_backend: loaded Vulkan backend from C:\Users\swaga_nsppntr\AppData\Local\Programs\Ollama\lib\ollama\vulkan\ggml-vulkan.dll time=2025-11-19T11:15:45.427+05:30 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 compiler=cgo(clang) ggml_backend_vk_get_device_memory called: uuid 8680a064-0400-0000-0002-000000000000 ggml_backend_vk_get_device_memory called: luid 0x000000000000ff6b ggml_dxgi_pdh_init called DXGI + PDH Initialized. Getting GPU free memory info [DXGI] Adapter Description: Intel(R) Arc(TM) 130V GPU (16GB), LUID: 0x000000000000FF6B, Dedicated: 0.12 GB, Shared: 27.45 GB [DXGI] Adapter Description: Microsoft Basic Render Driver, LUID: 0x000000000001038E, Dedicated: 0.00 GB, Shared: 27.45 GB Integrated GPU (Intel(R) Arc(TM) 130V GPU (16GB)) with LUID 0x000000000000ff6b detected. Shared Total: 29470189240.00 bytes (27.45 GB), Shared Usage: 1070800896.00 bytes (1.00 GB), Dedicated Total: 134217728.00 bytes (0.12 GB), Dedicated Usage: 0.00 bytes (0.00 GB) ggml_backend_vk_get_device_memory utilizing DXGI + PDH memory reporting free: 28533606072 total: 29604406968 time=2025-11-19T11:15:45.809+05:30 level=INFO source=runner.go:1271 msg=load request="{Operation:alloc LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:true KvSize:8192 KvCacheType: NumThreads:4 GPULayers:25[ID:8680a064-0400-0000-0002-000000000000 Layers:25(0..24)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" ggml_backend_vk_get_device_memory called: uuid 8680a064-0400-0000-0002-000000000000 ggml_backend_vk_get_device_memory called: luid 0x000000000000ff6b ggml_dxgi_pdh_init called DXGI + PDH Initialized. Getting GPU free memory info [DXGI] Adapter Description: Intel(R) Arc(TM) 130V GPU (16GB), LUID: 0x000000000000FF6B, Dedicated: 0.12 GB, Shared: 27.45 GB [DXGI] Adapter Description: Microsoft Basic Render Driver, LUID: 0x000000000001038E, Dedicated: 0.00 GB, Shared: 27.45 GB Integrated GPU (Intel(R) Arc(TM) 130V GPU (16GB)) with LUID 0x000000000000ff6b detected. Shared Total: 29470189240.00 bytes (27.45 GB), Shared Usage: 1070800896.00 bytes (1.00 GB), Dedicated Total: 134217728.00 bytes (0.12 GB), Dedicated Usage: 0.00 bytes (0.00 GB) ggml_backend_vk_get_device_memory utilizing DXGI + PDH memory reporting free: 28533606072 total: 29604406968 time=2025-11-19T11:15:51.463+05:30 level=INFO source=runner.go:1271 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:true KvSize:8192 KvCacheType: NumThreads:4 GPULayers:25[ID:8680a064-0400-0000-0002-000000000000 Layers:25(0..24)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2025-11-19T11:15:51.463+05:30 level=INFO source=ggml.go:482 msg="offloading 24 repeating layers to GPU" time=2025-11-19T11:15:51.463+05:30 level=INFO source=ggml.go:489 msg="offloading output layer to GPU" time=2025-11-19T11:15:51.463+05:30 level=INFO source=ggml.go:494 msg="offloaded 25/25 layers to GPU" time=2025-11-19T11:15:51.465+05:30 level=INFO source=device.go:240 msg="model weights" device=Vulkan0 size="11.8 GiB" time=2025-11-19T11:15:51.465+05:30 level=INFO source=device.go:245 msg="model weights" device=CPU size="1.1 GiB" time=2025-11-19T11:15:51.465+05:30 level=INFO source=device.go:251 msg="kv cache" device=Vulkan0 size="300.0 MiB" time=2025-11-19T11:15:51.465+05:30 level=INFO source=device.go:262 msg="compute graph" device=Vulkan0 size="110.6 MiB" time=2025-11-19T11:15:51.467+05:30 level=INFO source=device.go:267 msg="compute graph" device=CPU size="5.6 MiB" time=2025-11-19T11:15:51.468+05:30 level=INFO source=device.go:272 msg="total memory" size="13.2 GiB" time=2025-11-19T11:15:51.468+05:30 level=INFO source=sched.go:517 msg="loaded runners" count=1 time=2025-11-19T11:15:51.468+05:30 level=INFO source=server.go:1294 msg="waiting for llama runner to start responding" time=2025-11-19T11:15:51.469+05:30 level=INFO source=server.go:1328 msg="waiting for server to become available" status="llm server loading model" ``` ### OS Windows ### GPU Intel ### CPU Intel ### Ollama version v0.12.11
GiteaMirror added the vulkanperformancebug labels 2026-04-12 21:28:21 -05:00
GiteaMirror commented 2026-04-12 21:28:23 -05:00
Author
Owner
Copy Link

@charlescng commented on GitHub (Nov 20, 2025):

Testing with gemma3:12b on my Intel Arc B580 with the xe driver from Linux 6.17.

~35 t/s with ipex-llm (Ollama 0.9.3)
~15 t/s with Vulkan (Ollama 0.13.0)

time=2025-11-20T01:34:32.654Z level=INFO source=routes.go:1544 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GGML_VK_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:4096 OLLAMA_DEBUG:INFO OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434 OLLAMA_KEEP_ALIVE:2562047h47m16.854775807s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:1 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/root/.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_REMOTES:[ollama.com] OLLAMA_SCHED_SPREAD:false OLLAMA_VULKAN:true ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]"

time=2025-11-20T01:34:32.654Z level=INFO source=images.go:522 msg="total blobs: 14"

time=2025-11-20T01:34:32.655Z level=INFO source=images.go:529 msg="total unused blobs removed: 0"

time=2025-11-20T01:34:32.655Z level=INFO source=routes.go:1597 msg="Listening on [::]:11434 (version 0.13.0)"

time=2025-11-20T01:34:32.655Z level=INFO source=runner.go:67 msg="discovering available GPUs..."

time=2025-11-20T01:34:32.656Z level=INFO source=server.go:392 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 33719"

time=2025-11-20T01:34:32.764Z level=INFO source=server.go:392 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 36285"

time=2025-11-20T01:34:32.792Z level=INFO source=server.go:392 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 42775"

time=2025-11-20T01:34:32.809Z level=INFO source=types.go:42 msg="inference compute" id=86800be2-0000-0000-0600-000000000000 filter_id="" library=Vulkan compute=0.0 name=Vulkan0 description="Intel(R) Graphics (BMG G21)" libdirs=ollama,vulkan driver=0.0 pci_id=0000:06:00.0 type=discrete total="11.9 GiB" available="10.7 GiB"

time=2025-11-20T01:34:32.809Z level=INFO source=routes.go:1638 msg="entering low vram mode" "total vram"="11.9 GiB" threshold="20.0 GiB"

time=2025-11-20T01:34:59.897Z level=INFO source=server.go:392 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 43677"

time=2025-11-20T01:34:59.948Z level=WARN source=cpu_linux.go:130 msg="failed to parse CPU allowed micro secs" error="strconv.ParseInt: parsing \"max\": invalid syntax"

time=2025-11-20T01:35:00.093Z level=INFO source=server.go:209 msg="enabling flash attention"

time=2025-11-20T01:35:00.093Z level=INFO source=server.go:392 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --model /root/.ollama/models/blobs/sha256-e8ad13eff07a78d89926e9e8b882317d082ef5bf9768ad7b50fcdbbcd63748de --port 38295"

time=2025-11-20T01:35:00.094Z level=INFO source=sched.go:443 msg="system memory" total="15.6 GiB" free="15.5 GiB" free_swap="2.0 GiB"

time=2025-11-20T01:35:00.094Z level=INFO source=sched.go:450 msg="gpu memory" id=86800be2-0000-0000-0600-000000000000 library=Vulkan available="10.3 GiB" free="10.7 GiB" minimum="457.0 MiB" overhead="0 B"

time=2025-11-20T01:35:00.094Z level=INFO source=server.go:702 msg="loading model" "model layers"=49 requested=-1

time=2025-11-20T01:35:00.104Z level=INFO source=runner.go:1398 msg="starting ollama engine"

time=2025-11-20T01:35:00.104Z level=INFO source=runner.go:1433 msg="Server listening on 127.0.0.1:38295"

time=2025-11-20T01:35:00.105Z level=INFO source=runner.go:1271 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:true KvSize:4096 KvCacheType: NumThreads:2 GPULayers:49[ID:86800be2-0000-0000-0600-000000000000 Layers:49(0..48)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"

time=2025-11-20T01:35:00.160Z level=INFO source=ggml.go:136 msg="" architecture=gemma3 file_type=Q4_K_M name="" description="" num_tensors=1065 num_key_values=37

load_backend: loaded CPU backend from /usr/lib/ollama/libggml-cpu-haswell.so

ggml_vulkan: Found 1 Vulkan devices:

ggml_vulkan: 0 = Intel(R) Graphics (BMG G21) (Intel open-source Mesa driver) | uma: 0 | fp16: 1 | bf16: 0 | warp size: 32 | shared memory: 131072 | int dot: 1 | matrix cores: KHR_coopmat

load_backend: loaded Vulkan backend from /usr/lib/ollama/vulkan/libggml-vulkan.so

time=2025-11-20T01:35:00.190Z 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 compiler=cgo(gcc)

ggml_backend_vk_get_device_memory called: uuid 86800be2-0000-0000-0600-000000000000

ggml_backend_vk_get_device_memory called: luid 0x0000000000000000

time=2025-11-20T01:35:00.428Z level=INFO source=runner.go:1271 msg=load request="{Operation:alloc LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:true KvSize:4096 KvCacheType: NumThreads:2 GPULayers:49[ID:86800be2-0000-0000-0600-000000000000 Layers:49(0..48)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"

ggml_backend_vk_get_device_memory called: uuid 86800be2-0000-0000-0600-000000000000

ggml_backend_vk_get_device_memory called: luid 0x0000000000000000

time=2025-11-20T01:35:00.788Z level=INFO source=runner.go:1271 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:true KvSize:4096 KvCacheType: NumThreads:2 GPULayers:49[ID:86800be2-0000-0000-0600-000000000000 Layers:49(0..48)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"

time=2025-11-20T01:35:00.788Z level=INFO source=ggml.go:482 msg="offloading 48 repeating layers to GPU"

time=2025-11-20T01:35:00.788Z level=INFO source=ggml.go:489 msg="offloading output layer to GPU"

time=2025-11-20T01:35:00.788Z level=INFO source=ggml.go:494 msg="offloaded 49/49 layers to GPU"

time=2025-11-20T01:35:00.788Z level=INFO source=device.go:240 msg="model weights" device=Vulkan0 size="7.6 GiB"

time=2025-11-20T01:35:00.788Z level=INFO source=device.go:245 msg="model weights" device=CPU size="787.5 MiB"

time=2025-11-20T01:35:00.788Z level=INFO source=device.go:251 msg="kv cache" device=Vulkan0 size="736.0 MiB"

time=2025-11-20T01:35:00.788Z level=INFO source=device.go:262 msg="compute graph" device=Vulkan0 size="135.3 MiB"

time=2025-11-20T01:35:00.788Z level=INFO source=device.go:267 msg="compute graph" device=CPU size="7.5 MiB"

time=2025-11-20T01:35:00.788Z level=INFO source=device.go:272 msg="total memory" size="9.2 GiB"

time=2025-11-20T01:35:00.788Z level=INFO source=sched.go:517 msg="loaded runners" count=1

time=2025-11-20T01:35:00.788Z level=INFO source=server.go:1294 msg="waiting for llama runner to start responding"

time=2025-11-20T01:35:00.802Z level=INFO source=server.go:1328 msg="waiting for server to become available" status="llm server loading model"

time=2025-11-20T01:35:04.331Z level=INFO source=server.go:1332 msg="llama runner started in 4.24 seconds"
<!-- gh-comment-id:3555328975 --> @charlescng commented on GitHub (Nov 20, 2025): Testing with gemma3:12b on my Intel Arc B580 with the xe driver from Linux 6.17. ~35 t/s with [ipex-llm](https://github.com/ipex-llm/ipex-llm/releases/download/v2.3.0-nightly/ollama-ipex-llm-2.3.0b20250725-ubuntu.tgz) (Ollama 0.9.3) ~15 t/s with Vulkan (Ollama 0.13.0) ``` time=2025-11-20T01:34:32.654Z level=INFO source=routes.go:1544 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GGML_VK_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:4096 OLLAMA_DEBUG:INFO OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434 OLLAMA_KEEP_ALIVE:2562047h47m16.854775807s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:1 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/root/.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_REMOTES:[ollama.com] OLLAMA_SCHED_SPREAD:false OLLAMA_VULKAN:true ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]" time=2025-11-20T01:34:32.654Z level=INFO source=images.go:522 msg="total blobs: 14" time=2025-11-20T01:34:32.655Z level=INFO source=images.go:529 msg="total unused blobs removed: 0" time=2025-11-20T01:34:32.655Z level=INFO source=routes.go:1597 msg="Listening on [::]:11434 (version 0.13.0)" time=2025-11-20T01:34:32.655Z level=INFO source=runner.go:67 msg="discovering available GPUs..." time=2025-11-20T01:34:32.656Z level=INFO source=server.go:392 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 33719" time=2025-11-20T01:34:32.764Z level=INFO source=server.go:392 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 36285" time=2025-11-20T01:34:32.792Z level=INFO source=server.go:392 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 42775" time=2025-11-20T01:34:32.809Z level=INFO source=types.go:42 msg="inference compute" id=86800be2-0000-0000-0600-000000000000 filter_id="" library=Vulkan compute=0.0 name=Vulkan0 description="Intel(R) Graphics (BMG G21)" libdirs=ollama,vulkan driver=0.0 pci_id=0000:06:00.0 type=discrete total="11.9 GiB" available="10.7 GiB" time=2025-11-20T01:34:32.809Z level=INFO source=routes.go:1638 msg="entering low vram mode" "total vram"="11.9 GiB" threshold="20.0 GiB" time=2025-11-20T01:34:59.897Z level=INFO source=server.go:392 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 43677" time=2025-11-20T01:34:59.948Z level=WARN source=cpu_linux.go:130 msg="failed to parse CPU allowed micro secs" error="strconv.ParseInt: parsing \"max\": invalid syntax" time=2025-11-20T01:35:00.093Z level=INFO source=server.go:209 msg="enabling flash attention" time=2025-11-20T01:35:00.093Z level=INFO source=server.go:392 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --model /root/.ollama/models/blobs/sha256-e8ad13eff07a78d89926e9e8b882317d082ef5bf9768ad7b50fcdbbcd63748de --port 38295" time=2025-11-20T01:35:00.094Z level=INFO source=sched.go:443 msg="system memory" total="15.6 GiB" free="15.5 GiB" free_swap="2.0 GiB" time=2025-11-20T01:35:00.094Z level=INFO source=sched.go:450 msg="gpu memory" id=86800be2-0000-0000-0600-000000000000 library=Vulkan available="10.3 GiB" free="10.7 GiB" minimum="457.0 MiB" overhead="0 B" time=2025-11-20T01:35:00.094Z level=INFO source=server.go:702 msg="loading model" "model layers"=49 requested=-1 time=2025-11-20T01:35:00.104Z level=INFO source=runner.go:1398 msg="starting ollama engine" time=2025-11-20T01:35:00.104Z level=INFO source=runner.go:1433 msg="Server listening on 127.0.0.1:38295" time=2025-11-20T01:35:00.105Z level=INFO source=runner.go:1271 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:true KvSize:4096 KvCacheType: NumThreads:2 GPULayers:49[ID:86800be2-0000-0000-0600-000000000000 Layers:49(0..48)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2025-11-20T01:35:00.160Z level=INFO source=ggml.go:136 msg="" architecture=gemma3 file_type=Q4_K_M name="" description="" num_tensors=1065 num_key_values=37 load_backend: loaded CPU backend from /usr/lib/ollama/libggml-cpu-haswell.so ggml_vulkan: Found 1 Vulkan devices: ggml_vulkan: 0 = Intel(R) Graphics (BMG G21) (Intel open-source Mesa driver) | uma: 0 | fp16: 1 | bf16: 0 | warp size: 32 | shared memory: 131072 | int dot: 1 | matrix cores: KHR_coopmat load_backend: loaded Vulkan backend from /usr/lib/ollama/vulkan/libggml-vulkan.so time=2025-11-20T01:35:00.190Z 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 compiler=cgo(gcc) ggml_backend_vk_get_device_memory called: uuid 86800be2-0000-0000-0600-000000000000 ggml_backend_vk_get_device_memory called: luid 0x0000000000000000 time=2025-11-20T01:35:00.428Z level=INFO source=runner.go:1271 msg=load request="{Operation:alloc LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:true KvSize:4096 KvCacheType: NumThreads:2 GPULayers:49[ID:86800be2-0000-0000-0600-000000000000 Layers:49(0..48)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" ggml_backend_vk_get_device_memory called: uuid 86800be2-0000-0000-0600-000000000000 ggml_backend_vk_get_device_memory called: luid 0x0000000000000000 time=2025-11-20T01:35:00.788Z level=INFO source=runner.go:1271 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:true KvSize:4096 KvCacheType: NumThreads:2 GPULayers:49[ID:86800be2-0000-0000-0600-000000000000 Layers:49(0..48)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2025-11-20T01:35:00.788Z level=INFO source=ggml.go:482 msg="offloading 48 repeating layers to GPU" time=2025-11-20T01:35:00.788Z level=INFO source=ggml.go:489 msg="offloading output layer to GPU" time=2025-11-20T01:35:00.788Z level=INFO source=ggml.go:494 msg="offloaded 49/49 layers to GPU" time=2025-11-20T01:35:00.788Z level=INFO source=device.go:240 msg="model weights" device=Vulkan0 size="7.6 GiB" time=2025-11-20T01:35:00.788Z level=INFO source=device.go:245 msg="model weights" device=CPU size="787.5 MiB" time=2025-11-20T01:35:00.788Z level=INFO source=device.go:251 msg="kv cache" device=Vulkan0 size="736.0 MiB" time=2025-11-20T01:35:00.788Z level=INFO source=device.go:262 msg="compute graph" device=Vulkan0 size="135.3 MiB" time=2025-11-20T01:35:00.788Z level=INFO source=device.go:267 msg="compute graph" device=CPU size="7.5 MiB" time=2025-11-20T01:35:00.788Z level=INFO source=device.go:272 msg="total memory" size="9.2 GiB" time=2025-11-20T01:35:00.788Z level=INFO source=sched.go:517 msg="loaded runners" count=1 time=2025-11-20T01:35:00.788Z level=INFO source=server.go:1294 msg="waiting for llama runner to start responding" time=2025-11-20T01:35:00.802Z level=INFO source=server.go:1328 msg="waiting for server to become available" status="llm server loading model" time=2025-11-20T01:35:04.331Z level=INFO source=server.go:1332 msg="llama runner started in 4.24 seconds" ```
GiteaMirror commented 2026-04-12 21:28:23 -05:00
Author
Owner
Copy Link

@grover66 commented on GitHub (Nov 20, 2025):

Can confirm works well on my ACEMAGIC F3A AMD Ryzen AI 9 HX 370 Mini PC. LLMs using 32GBs of vram.

Glad to run any tests requested.
Mike :)

Here is hardware info:

ubuntu-desktop
description: Computer
width: 64 bits
capabilities: smp vsyscall32
*-core
description: Motherboard
physical id: 0
*-memory
description: System memory
physical id: 0
size: 80GiB
*-cpu
product: AMD Ryzen AI 9 HX 370 w/ Radeon 890M
vendor: Advanced Micro Devices [AMD]
physical id: 1
bus info: cpu@0
version: 26.36.0
size: 4807MHz
capacity: 5157MHz
width: 64 bits
capabilities: fpu fpu_exception wp vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp x86-64 constant_tsc rep_good amd_lbr_v2 nopl xtopology nonstop_tsc cpuid extd_apicid aperfmperf rapl pni pclmulqdq monitor ssse3 fma cx16 sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw ibs skinit wdt tce topoext perfctr_core perfctr_nb bpext perfctr_llc mwaitx cpb cat_l3 cdp_l3 hw_pstate ssbd mba perfmon_v2 ibrs ibpb stibp ibrs_enhanced vmmcall fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local user_shstk avx_vnni avx512_bf16 clzero irperf xsaveerptr rdpru wbnoinvd cppc arat npt lbrv svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold avic v_vmsave_vmload vgif x2avic v_spec_ctrl vnmi avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq rdpid bus_lock_detect movdiri movdir64b overflow_recov succor smca fsrm avx512_vp2intersect flush_l1d amd_lbr_pmc_freeze cpufreq
configuration: microcode=186662937

<!-- gh-comment-id:3560010683 --> @grover66 commented on GitHub (Nov 20, 2025): Can confirm works well on my ACEMAGIC F3A AMD Ryzen AI 9 HX 370 Mini PC. LLMs using 32GBs of vram. Glad to run any tests requested. Mike :) Here is hardware info: ubuntu-desktop description: Computer width: 64 bits capabilities: smp vsyscall32 *-core description: Motherboard physical id: 0 *-memory description: System memory physical id: 0 size: 80GiB *-cpu product: AMD Ryzen AI 9 HX 370 w/ Radeon 890M vendor: Advanced Micro Devices [AMD] physical id: 1 bus info: cpu@0 version: 26.36.0 size: 4807MHz capacity: 5157MHz width: 64 bits capabilities: fpu fpu_exception wp vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp x86-64 constant_tsc rep_good amd_lbr_v2 nopl xtopology nonstop_tsc cpuid extd_apicid aperfmperf rapl pni pclmulqdq monitor ssse3 fma cx16 sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw ibs skinit wdt tce topoext perfctr_core perfctr_nb bpext perfctr_llc mwaitx cpb cat_l3 cdp_l3 hw_pstate ssbd mba perfmon_v2 ibrs ibpb stibp ibrs_enhanced vmmcall fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local user_shstk avx_vnni avx512_bf16 clzero irperf xsaveerptr rdpru wbnoinvd cppc arat npt lbrv svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold avic v_vmsave_vmload vgif x2avic v_spec_ctrl vnmi avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq rdpid bus_lock_detect movdiri movdir64b overflow_recov succor smca fsrm avx512_vp2intersect flush_l1d amd_lbr_pmc_freeze cpufreq configuration: microcode=186662937
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 performance vulkan
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#8699
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?