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 #1902] Extremely slow memory allocation in WSL2 container #47605

New Issue
Closed
opened 2026-04-28 04:29:18 -05:00 by GiteaMirror · 7 comments
GiteaMirror commented 2026-04-28 04:29:18 -05:00
Owner
Copy Link

Originally created by @otavio-silva on GitHub (Jan 10, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/1902

Originally assigned to: @dhiltgen on GitHub.

Description

When trying to run ollama inside a container, memory allocation is extremely slow, something like 50 MB/s max. When in chat with the model, the container releases memory after some time if idle and if I run a prompt, it allocates it all over again.

Steps to reproduce

  1. Run the command podman run --device nvidia.com/gpu=all --security-opt label=disable --detach --volume .ollama:/root/.ollama -p 11434:11434 --name ollama-19 ollama/ollama:0.1.19
  2. Run the command podman exec -it ollama-19 ollama run dolphin-mixtral
  3. Wait for several minutes

System info

Nome do host:                              GE76RAIDER
Nome do sistema operacional:               Microsoft Windows 11 Pro
Versão do sistema operacional:             10.0.22631 N/A compilação 22631
Fabricante do sistema operacional:         Microsoft Corporation
Configuração do SO:                        Estação de trabalho autônoma
Tipo de compilação do sistema operacional: Multiprocessor Free
Proprietário registrado:                   otavioasilva@hotmail.com
Organização registrada:                    N/A
Identificação do produto:                  00330-80000-00000-AA520
Data da instalação original:               02/08/2023, 14:30:14
Tempo de Inicialização do Sistema:         10/01/2024, 12:32:44
Fabricante do sistema:                     Micro-Star International Co., Ltd.
Modelo do sistema:                         Raider GE76 12UHS
Tipo de sistema:                           x64-based PC
Processador(es):                           1 processador(es) instalado(s).
                                           [01]: Intel64 Family 6 Model 154 Stepping 3 GenuineIntel ~2900 Mhz
Versão do BIOS:                            American Megatrends International, LLC. E17K4IMS.20D, 26/06/2023
Pasta do Windows:                          C:\WINDOWS
Pasta do sistema:                          C:\WINDOWS\system32
Inicializar dispositivo:                   \Device\HarddiskVolume1
Localidade do sistema:                     pt-br;Português (Brasil)
Localidade de entrada:                     en-us;Inglês (Estados Unidos)
Fuso horário:                              (UTC-03:00) Brasília
Memória física total:                      65.237 MB
Memória física disponível:                 46.571 MB
Memória Virtual: Tamanho Máximo:           74.965 MB
Memória Virtual: Disponível:               50.991 MB
Memória Virtual: Em Uso:                   23.974 MB
Local(is) de arquivo de paginação:         C:\pagefile.sys
Domínio:                                   WORKGROUP
Servidor de Logon:                         \\GE76RAIDER
Hotfix(es):                                4 hotfix(es) instalado(s).
                                           [01]: KB5033920
                                           [02]: KB5027397
                                           [03]: KB5034123
                                           [04]: KB5032393
Placa(s) de Rede:                          3 NIC(s) instalado(s).
                                           [01]: Killer E3100G 2.5 Gigabit Ethernet Controller
                                                 Nome da conexão: Ethernet
                                                 Status:          Mídia desconectada
                                           [02]: Killer(R) Wi-Fi 6E AX1675i 160MHz Wireless Network Adapter (211NGW)
                                                 Nome da conexão: Wi-Fi
                                                 DHCP ativado:    Sim
                                                 Servidor DHCP:   192.168.1.1
                                                 Endereço(es) IP
                                                 [01]: 192.168.1.26
                                           [03]: TAP-Windows Adapter V9
                                                 Nome da conexão: TAP-Windows
                                                 Status:          Mídia desconectada
Requisitos do Hyper-V:                     Hipervisor detectado. Recursos necessários para o Hyper-V não serão exibidos.
Originally created by @otavio-silva on GitHub (Jan 10, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/1902 Originally assigned to: @dhiltgen on GitHub. # Description When trying to run ollama inside a container, memory allocation is extremely slow, something like 50 MB/s max. When in chat with the model, the container releases memory after some time if idle and if I run a prompt, it allocates it all over again. # Steps to reproduce 1. Run the command `podman run --device nvidia.com/gpu=all --security-opt label=disable --detach --volume .ollama:/root/.ollama -p 11434:11434 --name ollama-19 ollama/ollama:0.1.19` 2. Run the command `podman exec -it ollama-19 ollama run dolphin-mixtral` 3. Wait for several minutes # System info ``` Nome do host: GE76RAIDER Nome do sistema operacional: Microsoft Windows 11 Pro Versão do sistema operacional: 10.0.22631 N/A compilação 22631 Fabricante do sistema operacional: Microsoft Corporation Configuração do SO: Estação de trabalho autônoma Tipo de compilação do sistema operacional: Multiprocessor Free Proprietário registrado: otavioasilva@hotmail.com Organização registrada: N/A Identificação do produto: 00330-80000-00000-AA520 Data da instalação original: 02/08/2023, 14:30:14 Tempo de Inicialização do Sistema: 10/01/2024, 12:32:44 Fabricante do sistema: Micro-Star International Co., Ltd. Modelo do sistema: Raider GE76 12UHS Tipo de sistema: x64-based PC Processador(es): 1 processador(es) instalado(s). [01]: Intel64 Family 6 Model 154 Stepping 3 GenuineIntel ~2900 Mhz Versão do BIOS: American Megatrends International, LLC. E17K4IMS.20D, 26/06/2023 Pasta do Windows: C:\WINDOWS Pasta do sistema: C:\WINDOWS\system32 Inicializar dispositivo: \Device\HarddiskVolume1 Localidade do sistema: pt-br;Português (Brasil) Localidade de entrada: en-us;Inglês (Estados Unidos) Fuso horário: (UTC-03:00) Brasília Memória física total: 65.237 MB Memória física disponível: 46.571 MB Memória Virtual: Tamanho Máximo: 74.965 MB Memória Virtual: Disponível: 50.991 MB Memória Virtual: Em Uso: 23.974 MB Local(is) de arquivo de paginação: C:\pagefile.sys Domínio: WORKGROUP Servidor de Logon: \\GE76RAIDER Hotfix(es): 4 hotfix(es) instalado(s). [01]: KB5033920 [02]: KB5027397 [03]: KB5034123 [04]: KB5032393 Placa(s) de Rede: 3 NIC(s) instalado(s). [01]: Killer E3100G 2.5 Gigabit Ethernet Controller Nome da conexão: Ethernet Status: Mídia desconectada [02]: Killer(R) Wi-Fi 6E AX1675i 160MHz Wireless Network Adapter (211NGW) Nome da conexão: Wi-Fi DHCP ativado: Sim Servidor DHCP: 192.168.1.1 Endereço(es) IP [01]: 192.168.1.26 [03]: TAP-Windows Adapter V9 Nome da conexão: TAP-Windows Status: Mídia desconectada Requisitos do Hyper-V: Hipervisor detectado. Recursos necessários para o Hyper-V não serão exibidos. ```
GiteaMirror added the bugwindows labels 2026-04-28 04:29:18 -05:00
GiteaMirror commented 2026-04-28 04:29:21 -05:00
Author
Owner
Copy Link

@otavio-silva commented on GitHub (Jan 19, 2024):

Any news on this?

<!-- gh-comment-id:1900768686 --> @otavio-silva commented on GitHub (Jan 19, 2024): Any news on this?
GiteaMirror commented 2026-04-28 04:29:23 -05:00
Author
Owner
Copy Link

@Hansson0728 commented on GitHub (Jan 19, 2024):

Probably related to the timeout that unloads the model after 5 min

<!-- gh-comment-id:1901269641 --> @Hansson0728 commented on GitHub (Jan 19, 2024): Probably related to the timeout that unloads the model after 5 min
GiteaMirror commented 2026-04-28 04:29:24 -05:00
Author
Owner
Copy Link

@otavio-silva commented on GitHub (Jan 20, 2024):

@Hansson0728 I don't think they are related, although Ollama offloading the model while I'm still on a chat with it is definitely annoying.

<!-- gh-comment-id:1901507031 --> @otavio-silva commented on GitHub (Jan 20, 2024): @Hansson0728 I don't think they are related, although Ollama offloading the model while I'm still on a chat with it is definitely annoying.
GiteaMirror commented 2026-04-28 04:29:25 -05:00
Author
Owner
Copy Link

@phong-phuong commented on GitHub (Mar 8, 2024):

Are you using windows native folder as the volume? There are known performance issues with it.
Instead you use the native docker volume or the equivalent for podman.

<!-- gh-comment-id:1986548316 --> @phong-phuong commented on GitHub (Mar 8, 2024): Are you using windows native folder as the volume? There are known performance issues with it. Instead you use the native docker volume or the equivalent for podman.
GiteaMirror commented 2026-04-28 04:29:26 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Mar 12, 2024):

If it's not volume related, my suspicion is there may be an AV system that's causing a performance impact. (Windows Defender, etc.)

Do you see the same performance problems when running the native Windows version of Ollama?

<!-- gh-comment-id:1992280662 --> @dhiltgen commented on GitHub (Mar 12, 2024): If it's not volume related, my suspicion is there may be an AV system that's causing a performance impact. (Windows Defender, etc.) Do you see the same performance problems when running the native Windows version of Ollama?
GiteaMirror commented 2026-04-28 04:29:27 -05:00
Author
Owner
Copy Link

@otavio-silva commented on GitHub (Mar 14, 2024):

@dhiltgen the issue does not occur in the native Windows version, only in the container one

<!-- gh-comment-id:1997626994 --> @otavio-silva commented on GitHub (Mar 14, 2024): @dhiltgen the issue does not occur in the native Windows version, only in the container one
GiteaMirror commented 2026-04-28 04:29:28 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (May 10, 2024):

As mentioned by a few other folks I think this just may be resource constraints from running in WSL2 – Ollama now has a native Windows version you can download here: https://ollama.com/download/windows

<!-- gh-comment-id:2103664723 --> @jmorganca commented on GitHub (May 10, 2024): As mentioned by a few other folks I think this just may be resource constraints from running in WSL2 – Ollama now has a native Windows version you can download here: https://ollama.com/download/windows
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 windows
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#47605
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?