ollama

ollama

apps.detail.official

apps.detail.types.app from joly0's Repository

apps.detail.sections.overview

Official Ollama images for Nvidia or AMD GPUs. Intel Arc GPUs could potentially work with Vulkan enabled. NOTE: Extra Parameters needed for Nvidia: --gpus=all Additionally you can add a Variable called CUDA_VISIBLE_DEVICES to only use specific Nvidia GPU(s) by ID. Example: 0 or 0,1 Extra Parameters needed for AMD: --device='/dev/kfd' --device='/dev/dri' Additionally you can add a Variable called ROCR_VISIBLE_DEVICES to only use specific AMD GPU(s) by UUID. Example: GPU-67246603a11f0a21 or GPU-XXXXXXX,GPU-YYYYYYY Docs: https://docs.ollama.com/

apps.marketingCta.appInstallTitle

apps.marketingCta.appInstallDescription

apps.installHelp.stepOpen apps.installHelp.stepSearchApp apps.installHelp.stepReview apps.installHelp.stepInstall
apps.marketingCta.secondary

apps.detail.sections.requirements

Nvidia-Driver plugin (nVidia Support)

Radeon-TOP plugin (AMD Support)

apps.detail.sections.categories

AIOther

apps.downloadStats.title

156,616,385
apps.downloadStats.metrics.totalDownloads
9,145,985
apps.downloadStats.metrics.thisMonth
13,684,524
apps.downloadStats.metrics.avgPerMonth

apps.downloadStats.chart.totalOverTime

apps.downloadStats.chart.loading

apps.detail.sections.related

apps.detail.related.exploreCategories

apps.detail.related.exploreAll
AIOther

apps.detail.sections.links

apps.detail.links.supporthub.docker.comapps.detail.repositorySources.dockerHubhub.docker.comapps.detail.links.templateraw.githubusercontent.com

apps.detail.sections.details

apps.detail.details.repository
ollama/ollama
apps.detail.details.registry
https://hub.docker.com/r/ollama/ollama/
apps.detail.details.lastUpdated2026-07-23
apps.detail.details.firstSeen2023-11-08

apps.detail.sections.runtime

apps.detail.details.webui
http://[IP]:[PORT:11434]/
apps.detail.details.network
bridge
apps.detail.details.shell
bash
apps.detail.details.privileged
false

apps.detail.sections.configuration

DataPathrw
apps.detail.config.target
/root/.ollama
apps.detail.config.default
/mnt/user/appdata/ollama
apps.detail.config.value
/mnt/user/appdata/ollama
API Interface PortPorttcp

Port number where ollama listens on.

apps.detail.config.target
11434
apps.detail.config.default
11434
apps.detail.config.value
11434
OLLAMA_HOSTVariable

IP and Port the server binds to. Set to 127.0.0.1:11434 for internal only access.

apps.detail.config.default
0.0.0.0:11434
apps.detail.config.value
0.0.0.0:11434
OLLAMA_ORIGINSVariable

Comma-separated list of allowed CORS origins.

apps.detail.config.default
*
apps.detail.config.value
*
OLLAMA_KEEP_ALIVEVariable

How long a model stays in VRAM, e.g. 60m or 24h (Set to -1 for infinite, 0 for none).

apps.detail.config.default
5m
apps.detail.config.value
5m
OLLAMA_LOAD_TIMEOUTVariable

Timeout for stall detection during model loads.

apps.detail.config.default
5m
apps.detail.config.value
5m
OLLAMA_NUM_PARALLELVariable

Max number of parallel requests a single model can handle.

apps.detail.config.default
1
apps.detail.config.value
1
OLLAMA_CONTEXT_LENGTHVariable

Default context window (tokens) if not specified by the model.

apps.detail.config.default
4096
apps.detail.config.value
4096
OLLAMA_KV_CACHE_TYPEVariable

Quantization type for the K/V cache, e.g. f16, q8_0, q4_0.

apps.detail.config.default
f16
apps.detail.config.value
f16
OLLAMA_MODELSVariable

The path where model weights and blobs are stored.

apps.detail.config.default
/root/.ollama/models
apps.detail.config.value
/root/.ollama/models
OLLAMA_MAX_LOADED_MODELSVariable

Maximum number of models loaded per GPU at once (Set to 0 for infinite).

apps.detail.config.default
0
apps.detail.config.value
0
OLLAMA_MAX_QUEUEVariable

Max requests that can wait in line when the server is busy.

apps.detail.config.default
512
apps.detail.config.value
512
OLLAMA_DEBUGVariable

Log detail level: 0 for INFO, 1 for DEBUG, 2 for TRACE.

apps.detail.config.default
0|1|2
OLLAMA_GPU_OVERHEADVariable

Reserved VRAM (in bytes) to leave empty on each GPU.

apps.detail.config.default
0
apps.detail.config.value
0
OLLAMA_FLASH_ATTENTIONVariable

Enables experimental Flash Attention optimizations.

apps.detail.config.default
false|true
OLLAMA_SCHED_SPREADVariable

If true, always spreads model layers across all visible GPUs.

apps.detail.config.default
false|true
OLLAMA_MULTIUSER_CACHEVariable

Optimizes prompt caching when multiple users share a model.

apps.detail.config.default
false|true
OLLAMA_NOPRUNEVariable

If true, does not delete unused model blobs on startup.

apps.detail.config.default
false|true
OLLAMA_NOHISTORYVariable

Disables the readline history in the interactive CLI.

apps.detail.config.default
false|true
OLLAMA_NEW_ENGINEVariable

Enables the experimental new Ollama engine.

apps.detail.config.default
false|true
OLLAMA_VULKANVariable

Enables experimental Vulkan hardware acceleration.

apps.detail.config.default
false|true
HTTP_PROXYVariable

Proxy for downloading models over HTTP.

HTTPS_PROXYVariable

Proxy for downloading models over HTTPS.

NO_PROXYVariable

Comma-separate list of hosts/IPs that bypass the proxy.