github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #13805] GLM-4.7-Flash | Ollama 0.14.3-rc3 #34803

New Issue
Closed
opened 2026-04-22 18:40:55 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-22 18:40:55 -05:00
Owner
Copy Link

Originally created by @Burnarz on GitHub (Jan 20, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/13805

What is the issue?

Hello,

As said in the title, i'm testing Ollama 0.14.3-rc3, specifically for GLM-4.7-Flash.

Here's my log:
ollama -v ollama version is 0.14.3-rc3
ollama ps NAME ID SIZE PROCESSOR CONTEXT UNTIL glm-4.7-flash:latest ff14144f31df 51 GB 52%/48% CPU/GPU 32768 Forever

Here's my "systemctl edit ollama.service":

### Anything between here and the comment below will become the contents of the drop-in file

[Service]
Environment="OLLAMA_HOST=0.0.0.0:11434"
Environment="OLLAMA_KEEP_ALIVE=-1"
Environment="OLLAMA_CONTEXT_LENGTH=32768"
Environment="OLLAMA_FLASH_ATTENTION=1"

### Edits below this comment will be discarded


### /etc/systemd/system/ollama.service
# [Unit]
# Description=Ollama Service
# After=network-online.target
# 
# [Service]
# ExecStart=/usr/local/bin/ollama serve
# User=ollama
# Group=ollama
# Restart=always
# RestartSec=3
# Environment="PATH=/home/burnarz/.local/bin:/home/burnarz/.cargo/bin:/home/burnarz/.cargo/bin:/home/burnarz/.cargo/bin:/home/burnarz/.cargo/bin:/home/burnarz/.c>
# 
# [Install]
# WantedBy=default.target

Did i miss something ?
Isn't this model supposed to fit in 24Go Vram like the Qwen3 version ?

Relevant log output

journalctl -u ollama --no-pager --follow --pager-end
janv. 20 23:13:12 jarvis-server systemd[1]: Started ollama.service - Ollama Service.
janv. 20 23:13:12 jarvis-server ollama[1232]: time=2026-01-20T23:13:12.982Z level=INFO source=routes.go:1629 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:32768 OLLAMA_DEBUG:INFO OLLAMA_FLASH_ATTENTION:true 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:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/usr/share/ollama/.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:false ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]"
janv. 20 23:13:12 jarvis-server ollama[1232]: time=2026-01-20T23:13:12.996Z level=INFO source=images.go:501 msg="total blobs: 44"
janv. 20 23:13:12 jarvis-server ollama[1232]: time=2026-01-20T23:13:12.997Z level=INFO source=images.go:508 msg="total unused blobs removed: 0"
janv. 20 23:13:12 jarvis-server ollama[1232]: time=2026-01-20T23:13:12.997Z level=INFO source=routes.go:1682 msg="Listening on [::]:11434 (version 0.14.3-rc3)"
janv. 20 23:13:12 jarvis-server ollama[1232]: time=2026-01-20T23:13:12.998Z level=INFO source=runner.go:67 msg="discovering available GPUs..."
janv. 20 23:13:13 jarvis-server ollama[1232]: time=2026-01-20T23:13:13.000Z level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 46777"
janv. 20 23:13:13 jarvis-server ollama[1232]: time=2026-01-20T23:13:13.330Z level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 41863"
janv. 20 23:13:13 jarvis-server ollama[1232]: time=2026-01-20T23:13:13.533Z level=INFO source=runner.go:106 msg="experimental Vulkan support disabled.  To enable, set OLLAMA_VULKAN=1"
janv. 20 23:13:13 jarvis-server ollama[1232]: time=2026-01-20T23:13:13.533Z level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 45103"
janv. 20 23:13:13 jarvis-server ollama[1232]: time=2026-01-20T23:13:13.667Z level=INFO source=types.go:42 msg="inference compute" id=GPU-d0364f00-33d1-a9a6-d173-85839f5f872c filter_id="" library=CUDA compute=8.6 name=CUDA0 description="NVIDIA GeForce RTX 3090" libdirs=ollama,cuda_v12 driver=12.8 pci_id=0000:26:00.0 type=discrete total="24.0 GiB" available="23.6 GiB"
janv. 20 23:14:13 jarvis-server ollama[1232]: [GIN] 2026/01/20 - 23:14:13 | 200 |    7.321588ms |       127.0.0.1 | GET      "/api/version"
janv. 20 23:15:04 jarvis-server ollama[1232]: [GIN] 2026/01/20 - 23:15:04 | 200 |      16.859µs |       127.0.0.1 | HEAD     "/"
janv. 20 23:15:05 jarvis-server ollama[1232]: [GIN] 2026/01/20 - 23:15:05 | 200 |  188.717743ms |       127.0.0.1 | POST     "/api/show"
janv. 20 23:15:05 jarvis-server ollama[1232]: time=2026-01-20T23:15:05.306Z level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 38973"
janv. 20 23:15:05 jarvis-server ollama[1232]: time=2026-01-20T23:15:05.641Z level=INFO source=server.go:245 msg="enabling flash attention"
janv. 20 23:15:05 jarvis-server ollama[1232]: time=2026-01-20T23:15:05.641Z level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --model /usr/share/ollama/.ollama/models/blobs/sha256-cb6dfd23d780fa40505f9043ae62c7da85e6ec617cfa921dcd9dbb5a8e64ec67 --port 37871"
janv. 20 23:15:05 jarvis-server ollama[1232]: time=2026-01-20T23:15:05.642Z level=INFO source=sched.go:452 msg="system memory" total="15.5 GiB" free="13.5 GiB" free_swap="16.0 GiB"
janv. 20 23:15:05 jarvis-server ollama[1232]: time=2026-01-20T23:15:05.642Z level=INFO source=sched.go:459 msg="gpu memory" id=GPU-d0364f00-33d1-a9a6-d173-85839f5f872c library=CUDA available="23.1 GiB" free="23.6 GiB" minimum="457.0 MiB" overhead="0 B"
janv. 20 23:15:05 jarvis-server ollama[1232]: time=2026-01-20T23:15:05.642Z level=INFO source=server.go:755 msg="loading model" "model layers"=48 requested=-1
janv. 20 23:15:05 jarvis-server ollama[1232]: time=2026-01-20T23:15:05.651Z level=INFO source=runner.go:1405 msg="starting ollama engine"
janv. 20 23:15:05 jarvis-server ollama[1232]: time=2026-01-20T23:15:05.651Z level=INFO source=runner.go:1440 msg="Server listening on 127.0.0.1:37871"
janv. 20 23:15:05 jarvis-server ollama[1232]: time=2026-01-20T23:15:05.653Z level=INFO source=runner.go:1278 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:32768 KvCacheType: NumThreads:6 GPULayers:48[ID:GPU-d0364f00-33d1-a9a6-d173-85839f5f872c Layers:48(0..47)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
janv. 20 23:15:05 jarvis-server ollama[1232]: time=2026-01-20T23:15:05.698Z level=INFO source=ggml.go:136 msg="" architecture=glm4moelite file_type=Q4_K_M name="" description="" num_tensors=797 num_key_values=37
janv. 20 23:15:05 jarvis-server ollama[1232]: load_backend: loaded CPU backend from /usr/local/lib/ollama/libggml-cpu-haswell.so
janv. 20 23:15:05 jarvis-server ollama[1232]: ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
janv. 20 23:15:05 jarvis-server ollama[1232]: ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
janv. 20 23:15:05 jarvis-server ollama[1232]: ggml_cuda_init: found 1 CUDA devices:
janv. 20 23:15:05 jarvis-server ollama[1232]:   Device 0: NVIDIA GeForce RTX 3090, compute capability 8.6, VMM: yes, ID: GPU-d0364f00-33d1-a9a6-d173-85839f5f872c
janv. 20 23:15:05 jarvis-server ollama[1232]: load_backend: loaded CUDA backend from /usr/local/lib/ollama/cuda_v12/libggml-cuda.so
janv. 20 23:15:05 jarvis-server ollama[1232]: time=2026-01-20T23:15:05.861Z 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=500,520,600,610,700,750,800,860,890,900,1200 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(gcc)
janv. 20 23:15:06 jarvis-server ollama[1232]: time=2026-01-20T23:15:06.300Z level=INFO source=runner.go:1278 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:32768 KvCacheType: NumThreads:6 GPULayers:22[ID:GPU-d0364f00-33d1-a9a6-d173-85839f5f872c Layers:22(25..46)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
janv. 20 23:15:06 jarvis-server ollama[1232]: time=2026-01-20T23:15:06.423Z level=INFO source=runner.go:1278 msg=load request="{Operation:alloc LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:32768 KvCacheType: NumThreads:6 GPULayers:22[ID:GPU-d0364f00-33d1-a9a6-d173-85839f5f872c Layers:22(25..46)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
janv. 20 23:15:14 jarvis-server ollama[1232]: time=2026-01-20T23:15:14.766Z level=INFO source=runner.go:1278 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:32768 KvCacheType: NumThreads:6 GPULayers:22[ID:GPU-d0364f00-33d1-a9a6-d173-85839f5f872c Layers:22(25..46)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
janv. 20 23:15:14 jarvis-server ollama[1232]: time=2026-01-20T23:15:14.770Z level=INFO source=ggml.go:482 msg="offloading 22 repeating layers to GPU"
janv. 20 23:15:14 jarvis-server ollama[1232]: time=2026-01-20T23:15:14.772Z level=INFO source=ggml.go:486 msg="offloading output layer to CPU"
janv. 20 23:15:14 jarvis-server ollama[1232]: time=2026-01-20T23:15:14.772Z level=INFO source=ggml.go:494 msg="offloaded 22/48 layers to GPU"
janv. 20 23:15:14 jarvis-server ollama[1232]: time=2026-01-20T23:15:14.771Z level=INFO source=device.go:240 msg="model weights" device=CUDA0 size="8.4 GiB"
janv. 20 23:15:14 jarvis-server ollama[1232]: time=2026-01-20T23:15:14.774Z level=INFO source=device.go:245 msg="model weights" device=CPU size="9.0 GiB"
janv. 20 23:15:14 jarvis-server ollama[1232]: time=2026-01-20T23:15:14.774Z level=INFO source=device.go:251 msg="kv cache" device=CUDA0 size="13.8 GiB"
janv. 20 23:15:14 jarvis-server ollama[1232]: time=2026-01-20T23:15:14.774Z level=INFO source=device.go:256 msg="kv cache" device=CPU size="15.6 GiB"
janv. 20 23:15:14 jarvis-server ollama[1232]: time=2026-01-20T23:15:14.774Z level=INFO source=device.go:262 msg="compute graph" device=CUDA0 size="850.5 MiB"
janv. 20 23:15:14 jarvis-server ollama[1232]: time=2026-01-20T23:15:14.774Z level=INFO source=device.go:267 msg="compute graph" device=CPU size="27.5 MiB"
janv. 20 23:15:14 jarvis-server ollama[1232]: time=2026-01-20T23:15:14.774Z level=INFO source=device.go:272 msg="total memory" size="47.7 GiB"
janv. 20 23:15:14 jarvis-server ollama[1232]: time=2026-01-20T23:15:14.775Z level=INFO source=sched.go:526 msg="loaded runners" count=1
janv. 20 23:15:14 jarvis-server ollama[1232]: time=2026-01-20T23:15:14.776Z level=INFO source=server.go:1347 msg="waiting for llama runner to start responding"
janv. 20 23:15:14 jarvis-server ollama[1232]: time=2026-01-20T23:15:14.788Z level=INFO source=server.go:1381 msg="waiting for server to become available" status="llm server loading model"
janv. 20 23:15:18 jarvis-server ollama[1232]: time=2026-01-20T23:15:18.034Z level=INFO source=server.go:1381 msg="waiting for server to become available" status="llm server not responding"
janv. 20 23:15:18 jarvis-server ollama[1232]: time=2026-01-20T23:15:18.563Z level=INFO source=server.go:1381 msg="waiting for server to become available" status="llm server loading model"
janv. 20 23:15:37 jarvis-server ollama[1232]: time=2026-01-20T23:15:37.862Z level=INFO source=server.go:1385 msg="llama runner started in 32.22 seconds"
janv. 20 23:15:37 jarvis-server ollama[1232]: [GIN] 2026/01/20 - 23:15:37 | 200 | 32.779561288s |       127.0.0.1 | POST     "/api/generate"
janv. 20 23:15:46 jarvis-server ollama[1232]: [GIN] 2026/01/20 - 23:15:46 | 200 |     971.777µs |       127.0.0.1 | HEAD     "/"
janv. 20 23:15:46 jarvis-server ollama[1232]: [GIN] 2026/01/20 - 23:15:46 | 200 |    1.193025ms |       127.0.0.1 | GET      "/api/ps"
janv. 20 23:21:17 jarvis-server ollama[1232]: [GIN] 2026/01/20 - 23:21:17 | 200 |       16.52µs |       127.0.0.1 | HEAD     "/"
janv. 20 23:21:17 jarvis-server ollama[1232]: [GIN] 2026/01/20 - 23:21:17 | 200 |  219.033913ms |       127.0.0.1 | POST     "/api/show"
janv. 20 23:21:17 jarvis-server ollama[1232]: [GIN] 2026/01/20 - 23:21:17 | 200 |  200.665714ms |       127.0.0.1 | POST     "/api/generate"
janv. 20 23:21:22 jarvis-server ollama[1232]: [GIN] 2026/01/20 - 23:21:22 | 200 |       15.85µs |       127.0.0.1 | HEAD     "/"
janv. 20 23:21:22 jarvis-server ollama[1232]: [GIN] 2026/01/20 - 23:21:22 | 200 |       21.16µs |       127.0.0.1 | GET      "/api/ps"

OS

Linux

GPU

Nvidia

CPU

AMD

Ollama version

0.14.3-rc3

Originally created by @Burnarz on GitHub (Jan 20, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/13805 ### What is the issue? Hello, As said in the title, i'm testing Ollama 0.14.3-rc3, specifically for GLM-4.7-Flash. Here's my log: `ollama -v ollama version is 0.14.3-rc3 ` `ollama ps NAME ID SIZE PROCESSOR CONTEXT UNTIL glm-4.7-flash:latest ff14144f31df 51 GB 52%/48% CPU/GPU 32768 Forever ` Here's my "systemctl edit ollama.service": ```### Editing /etc/systemd/system/ollama.service.d/override.conf ### Anything between here and the comment below will become the contents of the drop-in file [Service] Environment="OLLAMA_HOST=0.0.0.0:11434" Environment="OLLAMA_KEEP_ALIVE=-1" Environment="OLLAMA_CONTEXT_LENGTH=32768" Environment="OLLAMA_FLASH_ATTENTION=1" ### Edits below this comment will be discarded ### /etc/systemd/system/ollama.service # [Unit] # Description=Ollama Service # After=network-online.target # # [Service] # ExecStart=/usr/local/bin/ollama serve # User=ollama # Group=ollama # Restart=always # RestartSec=3 # Environment="PATH=/home/burnarz/.local/bin:/home/burnarz/.cargo/bin:/home/burnarz/.cargo/bin:/home/burnarz/.cargo/bin:/home/burnarz/.cargo/bin:/home/burnarz/.c> # # [Install] # WantedBy=default.target ``` Did i miss something ? Isn't this model supposed to fit in 24Go Vram like the Qwen3 version ? ### Relevant log output ```shell journalctl -u ollama --no-pager --follow --pager-end janv. 20 23:13:12 jarvis-server systemd[1]: Started ollama.service - Ollama Service. janv. 20 23:13:12 jarvis-server ollama[1232]: time=2026-01-20T23:13:12.982Z level=INFO source=routes.go:1629 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:32768 OLLAMA_DEBUG:INFO OLLAMA_FLASH_ATTENTION:true 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:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/usr/share/ollama/.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:false ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]" janv. 20 23:13:12 jarvis-server ollama[1232]: time=2026-01-20T23:13:12.996Z level=INFO source=images.go:501 msg="total blobs: 44" janv. 20 23:13:12 jarvis-server ollama[1232]: time=2026-01-20T23:13:12.997Z level=INFO source=images.go:508 msg="total unused blobs removed: 0" janv. 20 23:13:12 jarvis-server ollama[1232]: time=2026-01-20T23:13:12.997Z level=INFO source=routes.go:1682 msg="Listening on [::]:11434 (version 0.14.3-rc3)" janv. 20 23:13:12 jarvis-server ollama[1232]: time=2026-01-20T23:13:12.998Z level=INFO source=runner.go:67 msg="discovering available GPUs..." janv. 20 23:13:13 jarvis-server ollama[1232]: time=2026-01-20T23:13:13.000Z level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 46777" janv. 20 23:13:13 jarvis-server ollama[1232]: time=2026-01-20T23:13:13.330Z level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 41863" janv. 20 23:13:13 jarvis-server ollama[1232]: time=2026-01-20T23:13:13.533Z level=INFO source=runner.go:106 msg="experimental Vulkan support disabled. To enable, set OLLAMA_VULKAN=1" janv. 20 23:13:13 jarvis-server ollama[1232]: time=2026-01-20T23:13:13.533Z level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 45103" janv. 20 23:13:13 jarvis-server ollama[1232]: time=2026-01-20T23:13:13.667Z level=INFO source=types.go:42 msg="inference compute" id=GPU-d0364f00-33d1-a9a6-d173-85839f5f872c filter_id="" library=CUDA compute=8.6 name=CUDA0 description="NVIDIA GeForce RTX 3090" libdirs=ollama,cuda_v12 driver=12.8 pci_id=0000:26:00.0 type=discrete total="24.0 GiB" available="23.6 GiB" janv. 20 23:14:13 jarvis-server ollama[1232]: [GIN] 2026/01/20 - 23:14:13 | 200 | 7.321588ms | 127.0.0.1 | GET "/api/version" janv. 20 23:15:04 jarvis-server ollama[1232]: [GIN] 2026/01/20 - 23:15:04 | 200 | 16.859µs | 127.0.0.1 | HEAD "/" janv. 20 23:15:05 jarvis-server ollama[1232]: [GIN] 2026/01/20 - 23:15:05 | 200 | 188.717743ms | 127.0.0.1 | POST "/api/show" janv. 20 23:15:05 jarvis-server ollama[1232]: time=2026-01-20T23:15:05.306Z level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 38973" janv. 20 23:15:05 jarvis-server ollama[1232]: time=2026-01-20T23:15:05.641Z level=INFO source=server.go:245 msg="enabling flash attention" janv. 20 23:15:05 jarvis-server ollama[1232]: time=2026-01-20T23:15:05.641Z level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --model /usr/share/ollama/.ollama/models/blobs/sha256-cb6dfd23d780fa40505f9043ae62c7da85e6ec617cfa921dcd9dbb5a8e64ec67 --port 37871" janv. 20 23:15:05 jarvis-server ollama[1232]: time=2026-01-20T23:15:05.642Z level=INFO source=sched.go:452 msg="system memory" total="15.5 GiB" free="13.5 GiB" free_swap="16.0 GiB" janv. 20 23:15:05 jarvis-server ollama[1232]: time=2026-01-20T23:15:05.642Z level=INFO source=sched.go:459 msg="gpu memory" id=GPU-d0364f00-33d1-a9a6-d173-85839f5f872c library=CUDA available="23.1 GiB" free="23.6 GiB" minimum="457.0 MiB" overhead="0 B" janv. 20 23:15:05 jarvis-server ollama[1232]: time=2026-01-20T23:15:05.642Z level=INFO source=server.go:755 msg="loading model" "model layers"=48 requested=-1 janv. 20 23:15:05 jarvis-server ollama[1232]: time=2026-01-20T23:15:05.651Z level=INFO source=runner.go:1405 msg="starting ollama engine" janv. 20 23:15:05 jarvis-server ollama[1232]: time=2026-01-20T23:15:05.651Z level=INFO source=runner.go:1440 msg="Server listening on 127.0.0.1:37871" janv. 20 23:15:05 jarvis-server ollama[1232]: time=2026-01-20T23:15:05.653Z level=INFO source=runner.go:1278 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:32768 KvCacheType: NumThreads:6 GPULayers:48[ID:GPU-d0364f00-33d1-a9a6-d173-85839f5f872c Layers:48(0..47)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" janv. 20 23:15:05 jarvis-server ollama[1232]: time=2026-01-20T23:15:05.698Z level=INFO source=ggml.go:136 msg="" architecture=glm4moelite file_type=Q4_K_M name="" description="" num_tensors=797 num_key_values=37 janv. 20 23:15:05 jarvis-server ollama[1232]: load_backend: loaded CPU backend from /usr/local/lib/ollama/libggml-cpu-haswell.so janv. 20 23:15:05 jarvis-server ollama[1232]: ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no janv. 20 23:15:05 jarvis-server ollama[1232]: ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no janv. 20 23:15:05 jarvis-server ollama[1232]: ggml_cuda_init: found 1 CUDA devices: janv. 20 23:15:05 jarvis-server ollama[1232]: Device 0: NVIDIA GeForce RTX 3090, compute capability 8.6, VMM: yes, ID: GPU-d0364f00-33d1-a9a6-d173-85839f5f872c janv. 20 23:15:05 jarvis-server ollama[1232]: load_backend: loaded CUDA backend from /usr/local/lib/ollama/cuda_v12/libggml-cuda.so janv. 20 23:15:05 jarvis-server ollama[1232]: time=2026-01-20T23:15:05.861Z 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=500,520,600,610,700,750,800,860,890,900,1200 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(gcc) janv. 20 23:15:06 jarvis-server ollama[1232]: time=2026-01-20T23:15:06.300Z level=INFO source=runner.go:1278 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:32768 KvCacheType: NumThreads:6 GPULayers:22[ID:GPU-d0364f00-33d1-a9a6-d173-85839f5f872c Layers:22(25..46)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" janv. 20 23:15:06 jarvis-server ollama[1232]: time=2026-01-20T23:15:06.423Z level=INFO source=runner.go:1278 msg=load request="{Operation:alloc LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:32768 KvCacheType: NumThreads:6 GPULayers:22[ID:GPU-d0364f00-33d1-a9a6-d173-85839f5f872c Layers:22(25..46)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" janv. 20 23:15:14 jarvis-server ollama[1232]: time=2026-01-20T23:15:14.766Z level=INFO source=runner.go:1278 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:32768 KvCacheType: NumThreads:6 GPULayers:22[ID:GPU-d0364f00-33d1-a9a6-d173-85839f5f872c Layers:22(25..46)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" janv. 20 23:15:14 jarvis-server ollama[1232]: time=2026-01-20T23:15:14.770Z level=INFO source=ggml.go:482 msg="offloading 22 repeating layers to GPU" janv. 20 23:15:14 jarvis-server ollama[1232]: time=2026-01-20T23:15:14.772Z level=INFO source=ggml.go:486 msg="offloading output layer to CPU" janv. 20 23:15:14 jarvis-server ollama[1232]: time=2026-01-20T23:15:14.772Z level=INFO source=ggml.go:494 msg="offloaded 22/48 layers to GPU" janv. 20 23:15:14 jarvis-server ollama[1232]: time=2026-01-20T23:15:14.771Z level=INFO source=device.go:240 msg="model weights" device=CUDA0 size="8.4 GiB" janv. 20 23:15:14 jarvis-server ollama[1232]: time=2026-01-20T23:15:14.774Z level=INFO source=device.go:245 msg="model weights" device=CPU size="9.0 GiB" janv. 20 23:15:14 jarvis-server ollama[1232]: time=2026-01-20T23:15:14.774Z level=INFO source=device.go:251 msg="kv cache" device=CUDA0 size="13.8 GiB" janv. 20 23:15:14 jarvis-server ollama[1232]: time=2026-01-20T23:15:14.774Z level=INFO source=device.go:256 msg="kv cache" device=CPU size="15.6 GiB" janv. 20 23:15:14 jarvis-server ollama[1232]: time=2026-01-20T23:15:14.774Z level=INFO source=device.go:262 msg="compute graph" device=CUDA0 size="850.5 MiB" janv. 20 23:15:14 jarvis-server ollama[1232]: time=2026-01-20T23:15:14.774Z level=INFO source=device.go:267 msg="compute graph" device=CPU size="27.5 MiB" janv. 20 23:15:14 jarvis-server ollama[1232]: time=2026-01-20T23:15:14.774Z level=INFO source=device.go:272 msg="total memory" size="47.7 GiB" janv. 20 23:15:14 jarvis-server ollama[1232]: time=2026-01-20T23:15:14.775Z level=INFO source=sched.go:526 msg="loaded runners" count=1 janv. 20 23:15:14 jarvis-server ollama[1232]: time=2026-01-20T23:15:14.776Z level=INFO source=server.go:1347 msg="waiting for llama runner to start responding" janv. 20 23:15:14 jarvis-server ollama[1232]: time=2026-01-20T23:15:14.788Z level=INFO source=server.go:1381 msg="waiting for server to become available" status="llm server loading model" janv. 20 23:15:18 jarvis-server ollama[1232]: time=2026-01-20T23:15:18.034Z level=INFO source=server.go:1381 msg="waiting for server to become available" status="llm server not responding" janv. 20 23:15:18 jarvis-server ollama[1232]: time=2026-01-20T23:15:18.563Z level=INFO source=server.go:1381 msg="waiting for server to become available" status="llm server loading model" janv. 20 23:15:37 jarvis-server ollama[1232]: time=2026-01-20T23:15:37.862Z level=INFO source=server.go:1385 msg="llama runner started in 32.22 seconds" janv. 20 23:15:37 jarvis-server ollama[1232]: [GIN] 2026/01/20 - 23:15:37 | 200 | 32.779561288s | 127.0.0.1 | POST "/api/generate" janv. 20 23:15:46 jarvis-server ollama[1232]: [GIN] 2026/01/20 - 23:15:46 | 200 | 971.777µs | 127.0.0.1 | HEAD "/" janv. 20 23:15:46 jarvis-server ollama[1232]: [GIN] 2026/01/20 - 23:15:46 | 200 | 1.193025ms | 127.0.0.1 | GET "/api/ps" janv. 20 23:21:17 jarvis-server ollama[1232]: [GIN] 2026/01/20 - 23:21:17 | 200 | 16.52µs | 127.0.0.1 | HEAD "/" janv. 20 23:21:17 jarvis-server ollama[1232]: [GIN] 2026/01/20 - 23:21:17 | 200 | 219.033913ms | 127.0.0.1 | POST "/api/show" janv. 20 23:21:17 jarvis-server ollama[1232]: [GIN] 2026/01/20 - 23:21:17 | 200 | 200.665714ms | 127.0.0.1 | POST "/api/generate" janv. 20 23:21:22 jarvis-server ollama[1232]: [GIN] 2026/01/20 - 23:21:22 | 200 | 15.85µs | 127.0.0.1 | HEAD "/" janv. 20 23:21:22 jarvis-server ollama[1232]: [GIN] 2026/01/20 - 23:21:22 | 200 | 21.16µs | 127.0.0.1 | GET "/api/ps" ``` ### OS Linux ### GPU Nvidia ### CPU AMD ### Ollama version 0.14.3-rc3
GiteaMirror added the bug label 2026-04-22 18:40:55 -05:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#34803
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?