[GH-ISSUE #6006] Docker version of Ollama model loads slowly #29516

New Issue

GiteaMirror · 2026-04-22T08:28:12-05:00

GiteaMirror commented

2026-04-22 08:28:12 -05:00

Originally created by @billowssun on GitHub (Jul 27, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/6006

Originally assigned to: @dhiltgen on GitHub.

What is the issue?

OS

No response

GPU

No response

CPU

No response

Ollama version

No response

Originally created by @billowssun on GitHub (Jul 27, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/6006 Originally assigned to: @dhiltgen on GitHub. ### What is the issue? ![image](https://github.com/user-attachments/assets/7897f2a4-3a33-4fc7-9ca5-eac8b1839431) ### OS _No response_ ### GPU _No response_ ### CPU _No response_ ### Ollama version _No response_

GiteaMirror added the wsl performance windows labels 2026-04-22 08:28:12 -05:00

GiteaMirror closed this issue

2026-04-22 08:28:13 -05:00

GiteaMirror commented

2026-04-22 08:28:15 -05:00

@billowssun commented on GitHub (Jul 27, 2024):

@billowssun commented on GitHub (Jul 27, 2024): ![image](https://github.com/user-attachments/assets/9c3476e1-da62-4c4e-a079-c6b04c8eb7ff)

GiteaMirror commented

2026-04-22 08:28:16 -05:00

@mxmp210 commented on GitHub (Jul 27, 2024):

Is docker running on WSL2 backend? If then move the model in WSL2's HDD space some where in your user folder, it's technically a VM extension and filesystem is slower due to system calls being translated between two kernels. If not please provide further information on environment, OS, system specs, GPU etc. Attach ollama log file.

@mxmp210 commented on GitHub (Jul 27, 2024): Is docker running on WSL2 backend? If then move the model in WSL2's HDD space some where in your user folder, it's technically a VM extension and filesystem is slower due to system calls being translated between two kernels. If not please provide further information on environment, OS, system specs, GPU etc. Attach ollama log file.

GiteaMirror commented

2026-04-22 08:28:17 -05:00

@billowssun commented on GitHub (Aug 4, 2024):

Is docker running on WSL2 backend? If then move the model in WSL2's HDD space some where in your user folder, it's technically a VM extension and filesystem is slower due to system calls being translated between two kernels. If not please provide further information on environment, OS, system specs, GPU etc. Attach ollama log file.

I found the root of the problem. It's because mapping the local directory causes the large model to load slowly. If file path mapping is not used, loading materials would be very fast

@billowssun commented on GitHub (Aug 4, 2024): > Is docker running on WSL2 backend? If then move the model in WSL2's HDD space some where in your user folder, it's technically a VM extension and filesystem is slower due to system calls being translated between two kernels. If not please provide further information on environment, OS, system specs, GPU etc. Attach ollama log file. I found the root of the problem. It's because mapping the local directory causes the large model to load slowly. If file path mapping is not used, loading materials would be very fast

GiteaMirror commented

2026-04-22 08:28:18 -05:00

@mxmp210 commented on GitHub (Aug 4, 2024):

Yes, it works because docker volumes load from Linux mapped filesystem, and it has no extra system call overhead. So, it's not a bug, this behaviour is expected.

It is the technical limitation of WSL2 filesystem architecture.

@mxmp210 commented on GitHub (Aug 4, 2024): Yes, it works because docker volumes load from Linux mapped filesystem, and it has no extra system call overhead. So, it's not a bug, this behaviour is expected. It is the technical limitation of WSL2 filesystem architecture.

GiteaMirror commented

2026-04-22 08:28:19 -05:00

@jmorganca commented on GitHub (Sep 4, 2024):

Hi @billowssun, yes, while WSL2's filesystem mapping is very fast, it still may have some performance constraints that running on Windows directly may not have, including not being able to memory map chunks of the model into memory.

@jmorganca commented on GitHub (Sep 4, 2024): Hi @billowssun, yes, while WSL2's filesystem mapping is very fast, it still may have some performance constraints that running on Windows directly may not have, including not being able to memory map chunks of the model into memory.

GiteaMirror commented

2026-04-22 08:28:19 -05:00

@dhiltgen commented on GitHub (Sep 5, 2024):

I think we can close this one. When using WSL2, I/O back to the NTFS filesystem can be slow, so using the native linux filesystem on the vhd will be much faster.

@dhiltgen commented on GitHub (Sep 5, 2024): I think we can close this one. When using WSL2, I/O back to the NTFS filesystem can be slow, so using the native linux filesystem on the vhd will be much faster.

GiteaMirror commented

2026-04-22 08:28:20 -05:00

@agibson-fl commented on GitHub (Oct 16, 2024):

Is docker running on WSL2 backend? If then move the model in WSL2's HDD space some where in your user folder, it's technically a VM extension and filesystem is slower due to system calls being translated between two kernels. If not please provide further information on environment, OS, system specs, GPU etc. Attach ollama log file.

@mxmp210 I'm having the same issue as reported in this issue. However, I'm not exactly following this guidance to get around the issue.

When I look under Resources in Docker Desktop, it shows WSL 2 backed and that the disk image location is in C:\Users\owner\AppData\Local\Docker\wsl

I have the following volumes setup on my docker run command.

-v C:\Users\owner\Documents\docker\ollama\ollama:/root/.ollama `
-v C:\Users\owner\Documents\docker\ollama\data:/app/backend/data `

Where do I need to move the ollama and data folders? Can you be more explicit?

@agibson-fl commented on GitHub (Oct 16, 2024): > Is docker running on WSL2 backend? If then move the model in WSL2's HDD space some where in your user folder, it's technically a VM extension and filesystem is slower due to system calls being translated between two kernels. If not please provide further information on environment, OS, system specs, GPU etc. Attach ollama log file. @mxmp210 I'm having the same issue as reported in this issue. However, I'm not exactly following this guidance to get around the issue. When I look under Resources in Docker Desktop, it shows WSL 2 backed and that the disk image location is in `C:\Users\owner\AppData\Local\Docker\wsl` I have the following volumes setup on my docker run command. ``` -v C:\Users\owner\Documents\docker\ollama\ollama:/root/.ollama ` -v C:\Users\owner\Documents\docker\ollama\data:/app/backend/data ` ``` Where do I need to move the ollama and data folders? Can you be more explicit?

GiteaMirror commented

2026-04-22 08:28:20 -05:00

@mxmp210 commented on GitHub (Oct 17, 2024):

Where do I need to move the ollama and data folders? Can you be more explicit?

Anything in your home folder /home and root directory / except /mnt/<drive_letter> resides inside virtual disk, other devices in /mnt are mounted via qemu compatibility layer. That is the core reason why other paths are slower as the layer is responsible to translate Linux system calls to Windows compatible system calls.

Use user's home directory and it will have native like performance. Or you can use volume declaration without bind mount, that will store volumes inside wsl filesystem.

Hope that helps!

@mxmp210 commented on GitHub (Oct 17, 2024): > Where do I need to move the ollama and data folders? Can you be more explicit? Anything in your home folder `/home` and root directory `/` except `/mnt/<drive_letter>` resides inside virtual disk, other devices in `/mnt` are mounted via qemu compatibility layer. That is the core reason why other paths are slower as the layer is responsible to translate Linux system calls to Windows compatible system calls. Use user's home directory and it will have native like performance. Or you can use volume declaration without bind mount, that will store volumes inside wsl filesystem. Hope that helps!

GiteaMirror commented

2026-04-22 08:28:21 -05:00

@agibson-fl commented on GitHub (Oct 17, 2024):

@mxmp210 The default location for models inside the container seems to be /root/.ollama. So I setup my volume as such:

-v C:\Users\owner\Documents\docker\ollama\ollama:/root/.ollama `

However, when i remove this, I have 0 problems running the models. As a cost of making this change though, my downloaded models won't persist which is annoying since they're quite large. I'm STILL not following what you're saying to change to fix this. Can I add back the volume but a different windows path that would be faster and allow the models to load? All your suggestions refer to Linux paths I'm presuming inside the container. Do you have an example volume mount where I can persist my models beyond destroying/recreating the container AND have the models work when loaded, for example?

@agibson-fl commented on GitHub (Oct 17, 2024): @mxmp210 The default location for models inside the container seems to be /root/.ollama. So I setup my volume as such: ``` -v C:\Users\owner\Documents\docker\ollama\ollama:/root/.ollama ` ``` However, when i remove this, I have 0 problems running the models. As a cost of making this change though, my downloaded models won't persist which is annoying since they're quite large. I'm STILL not following what you're saying to change to fix this. Can I add back the volume but a different windows path that would be faster and allow the models to load? All your suggestions refer to Linux paths I'm presuming inside the container. Do you have an example volume mount where I can persist my models beyond destroying/recreating the container AND have the models work when loaded, for example?

GiteaMirror commented

2026-04-22 08:28:21 -05:00

@mxmp210 commented on GitHub (Oct 17, 2024):

-v C:\Users\owner\Documents\docker\ollama\ollama:/root/.ollama `

This translates to /mnt/c/Users/owner/Documents/docker/ollama/ollama:/root/.ollama

What you need is to create an explicit volume via docker volume create ollama_data and then reference it like -v ollama_data:/root/.ollama that ensures /root/.ollama path resides at /var/lib/docker/volumes/ which is the default location for the volumes managed by docker in most linux distros. This location happens to be outside /mnt/<location> thus gives the performance.

If you are using docker-compose :

services:
  ollama:
    ...
    volumes:
      - ollama_data:/root/.ollama
 
# Declare volume here - docker will create it / reference it & reuse it as long as it exists.      
volumes:
  ollama_data:
    #external: true # Only needed if volume already exists from external sources

Declaring volume keeps the data on disk as long as volume exists with docker. It will stay persistent unlike temporary volumes that are created on-the-go basis.

Please read docker volumes documentation for more details, if you are still having trouble understanding how docker volumes work.

@mxmp210 commented on GitHub (Oct 17, 2024): > ``` > -v C:\Users\owner\Documents\docker\ollama\ollama:/root/.ollama ` > ``` This translates to `/mnt/c/Users/owner/Documents/docker/ollama/ollama:/root/.ollama` What you need is to create an explicit volume via `docker volume create ollama_data` and then reference it like `-v ollama_data:/root/.ollama` that ensures `/root/.ollama` path resides at `/var/lib/docker/volumes/` which is the default location for the volumes managed by docker in most linux distros. This location happens to be outside `/mnt/<location>` thus gives the performance. If you are using docker-compose : ```yaml services: ollama: ... volumes: - ollama_data:/root/.ollama # Declare volume here - docker will create it / reference it & reuse it as long as it exists. volumes: ollama_data: #external: true # Only needed if volume already exists from external sources ``` Declaring volume keeps the data on disk as long as volume exists with docker. It will stay persistent unlike temporary volumes that are created on-the-go basis. Please read [docker volumes documentation](https://docs.docker.com/engine/storage/volumes/) for more details, if you are still having trouble understanding how docker volumes work.

GiteaMirror commented

2026-04-22 08:28:22 -05:00

@agibson-fl commented on GitHub (Oct 17, 2024):

@mxmp210 I follow this. Thank you for the more clear, direct example!

@agibson-fl commented on GitHub (Oct 17, 2024): @mxmp210 I follow this. Thank you for the more clear, direct example!

GiteaMirror commented

2026-04-22 08:28:22 -05:00

@Milor123 commented on GitHub (Dec 19, 2024):

-v C:\Users\owner\Documents\docker\ollama\ollama:/root/.ollama `
This translates to /mnt/c/Users/owner/Documents/docker/ollama/ollama:/root/.ollama

What you need is to create an explicit volume via docker volume create ollama_data and then reference it like -v ollama_data:/root/.ollama that ensures /root/.ollama path resides at /var/lib/docker/volumes/ which is the default location for the volumes managed by docker in most linux distros. This location happens to be outside /mnt/<location> thus gives the performance.

If you are using docker-compose :
services:
  ollama:
    ...
    volumes:
      - ollama_data:/root/.ollama
 
# Declare volume here - docker will create it / reference it & reuse it as long as it exists.      
volumes:
  ollama_data:
    #external: true # Only needed if volume already exists from external sources
Declaring volume keeps the data on disk as long as volume exists with docker. It will stay persistent unlike temporary volumes that are created on-the-go basis.

Please read docker volumes documentation for more details, if you are still having trouble understanding how docker volumes work.

Ohh excellent, I came from linux and now I'm on windows, a lot of things have happened to me, and thanks to your comment I could understand and solve the problem.

My ollama was very slow, but since I moved all my files to the volume inside WSL then they load very fast as in linux.
Thanks guys!❤️

@Milor123 commented on GitHub (Dec 19, 2024): > > ``` > > -v C:\Users\owner\Documents\docker\ollama\ollama:/root/.ollama ` > > ``` > > This translates to `/mnt/c/Users/owner/Documents/docker/ollama/ollama:/root/.ollama` > > What you need is to create an explicit volume via `docker volume create ollama_data` and then reference it like `-v ollama_data:/root/.ollama` that ensures `/root/.ollama` path resides at `/var/lib/docker/volumes/` which is the default location for the volumes managed by docker in most linux distros. This location happens to be outside `/mnt/<location>` thus gives the performance. > > If you are using docker-compose : > > ```yaml > services: > ollama: > ... > volumes: > - ollama_data:/root/.ollama > > # Declare volume here - docker will create it / reference it & reuse it as long as it exists. > volumes: > ollama_data: > #external: true # Only needed if volume already exists from external sources > ``` > > Declaring volume keeps the data on disk as long as volume exists with docker. It will stay persistent unlike temporary volumes that are created on-the-go basis. > > Please read [docker volumes documentation](https://docs.docker.com/engine/storage/volumes/) for more details, if you are still having trouble understanding how docker volumes work. Ohh excellent, I came from linux and now I'm on windows, a lot of things have happened to me, and thanks to your comment I could understand and solve the problem. My ollama was very slow, but since I moved all my files to the volume inside WSL then they load very fast as in linux. Thanks guys!❤️

GiteaMirror commented

2026-04-22 08:28:23 -05:00

@gitnlsn commented on GitHub (Aug 11, 2025):

Hi.

I'm running llama3:1b in ollama docker. It seems that after some idle time the next call takes longer. Why I ask? Is it docker configuration or should I run ollama without docker?

I'm not expert at docker performance.

@gitnlsn commented on GitHub (Aug 11, 2025): Hi. I'm running llama3:1b in ollama docker. It seems that after some idle time the next call takes longer. Why I ask? Is it docker configuration or should I run ollama without docker? I'm not expert at docker performance.

GiteaMirror commented

2026-04-22 08:28:24 -05:00

@TafadzwaD commented on GitHub (Sep 1, 2025):

Hi.

I'm running llama3:1b in ollama docker. It seems that after some idle time the next call takes longer. Why I ask? Is it docker configuration or should I run ollama without docker?

I'm not expert at docker performance.

@gitnlsn You can specify OLLAMA_KEEP_ALIVE, environment variable, when you run your ollama to stop the model from being offloaded from memory when idle. This will solve your cold start issue, the downside is that ollama ends up holding memory it is not using when idle.

@TafadzwaD commented on GitHub (Sep 1, 2025): > Hi. > > I'm running llama3:1b in ollama docker. It seems that after some idle time the next call takes longer. Why I ask? Is it docker configuration or should I run ollama without docker? > > I'm not expert at docker performance. @gitnlsn You can specify [`OLLAMA_KEEP_ALIVE`](https://github.com/ollama/ollama/pull/3094), environment variable, when you run your ollama to stop the model from being offloaded from memory when idle. This will solve your cold start issue, the downside is that ollama ends up holding memory it is not using when idle.

Sign in to join this conversation.

Branches Tags

main

dhiltgen/ci

parth-launch-plan-gating

hoyyeva/anthropic-reference-images-path

parth-anthropic-reference-images-path

brucemacd/download-before-remove

hoyyeva/editor-config-repair

parth-mlx-decode-checkpoints

parth-launch-codex-app

hoyyeva/fix-codex-model-metadata-warning

hoyyeva/qwen

parth/hide-claude-desktop-till-release

hoyyeva/opencode-image-modality

parth-add-claude-code-autoinstall

release_v0.22.0

pdevine/manifest-list

codex/fix-codex-model-metadata-warning

pdevine/addressable-manifest

brucemacd/launch-fetch-reccomended

jmorganca/llama-compat

launch-copilot-cli

hoyyeva/opencode-thinking

release_v0.20.7

parth-auto-save-backup

parth-test

jmorganca/gemma4-audio-replacements

fix-manifest-digest-on-pull

hoyyeva/vscode-improve

brucemacd/install-server-wait

parth/update-claude-docs

brucemac/start-ap-install

pdevine/mlx-update

pdevine/qwen35_vision

drifkin/api-show-fallback

mintlify/image-generation-1773352582

hoyyeva/server-context-length-local-config

jmorganca/faster-reptition-penalties

jmorganca/convert-nemotron

parth-pi-thinking

pdevine/sampling-penalties

jmorganca/fix-create-quantization-memory

dongchen/resumable_transfer_fix

pdevine/sampling-cache-error

jessegross/mlx-usage

hoyyeva/openclaw-config

hoyyeva/app-html

pdevine/qwen3next

brucemacd/sign-sh-install

brucemacd/tui-update

brucemacd/usage-api

jmorganca/launch-empty

fix-app-dist-embed

mxyng/mlx-compile

mxyng/mlx-quant

mxyng/mlx-glm4.7

mxyng/mlx

brucemacd/simplify-model-picker

jmorganca/qwen3-concurrent

fix-glm-4.7-flash-mla-config

drifkin/qwen3-coder-opening-tag

brucemacd/usage-cli

fix-cuda12-fattn-shmem

ollama-imagegen-docs

parth/fix-multiline-inputs

brucemacd/config-docs

mxyng/model-files

mxyng/simple-execute

fix-imagegen-ollama-models

mxyng/async-upload

jmorganca/lazy-no-dtype-changes

imagegen-auto-detect-create

parth/decrease-concurrent-download-hf

fix-mlx-quantize-init

jmorganca/x-cleanup

usage

imagegen-readme

jmorganca/glm-image

mlx-gpu-cd

jmorganca/imagegen-modelfile

parth/agent-skills

parth/agent-allowlist

parth/signed-in-offline

parth/agents

parth/fix-context-chopping

improve-cloud-flow

parth/add-models-websearch

parth/prompt-renderer-mcp

jmorganca/native-settings

jmorganca/download-stream-hash

jmorganca/client2-rebased

brucemacd/oai-chat-req-multipart

jessegross/multi_chunk_reserve

grace/additional-omit-empty

grace/mistral-3-large

mxyng/tokenizer2

mxyng/tokenizer

jessegross/flash

hoyyeva/windows-nacked-app

mxyng/cleanup-attention

grace/deepseek-parser

hoyyeva/remember-unsent-prompt

parth/add-lfs-pointer-error-conversion

parth/olmo2-test2

hoyyeva/ollama-launchagent-plist

nicole/olmo-model

parth/olmo-test

mxyng/remove-embedded

parth/render-template

jmorganca/intellect-3

parth/remove-prealloc-linter

jmorganca/cmd-eval

nicole/nomic-embed-text-fix

mxyng/lint-2

hoyyeva/add-gemini-3-pro-preview

hoyyeva/load-model-list

mxyng/expand-path

mxyng/environ-2

hoyyeva/deeplink-json-encoding

parth/improve-tool-calling-tests

hoyyeva/conversation

hoyyeva/assistant-edit-response

hoyyeva/thinking

origin/brucemacd/invalid-char-i-err

parth/improve-tool-calling

jmorganca/required-omitempty

grace/qwen3-vl-tests

mxyng/iter-client

parth/docs-readme

nicole/embed-test

pdevine/integration-benchstat

parth/remove-generate-cmd

parth/add-toolcall-id

mxyng/server-tests

jmorganca/glm-4.6

jmorganca/gin-h-compat

drifkin/stable-tool-args

pdevine/qwen3-more-thinking

parth/add-websearch-client

nicole/websearch_local

jmorganca/qwen3-coder-updates

grace/deepseek-v3-migration-tests

mxyng/fix-create

jmorganca/cloud-errors

pdevine/parser-tidy

revert-12233-parth/simplify-entrypoints-runner

parth/enable-so-gpt-oss

brucemacd/qwen3vl

jmorganca/readme-simplify

parth/gpt-oss-structured-outputs

revert-12039-jmorganca/tools-braces

mxyng/embeddings

mxyng/gguf

mxyng/benchmark

mxyng/types-null

parth/move-parsing

mxyng/gemma2

jmorganca/docs

mxyng/16-bit

mxyng/create-stdin

pdevine/authorizedkeys

mxyng/quant

parth/opt-in-error-context-window

brucemacd/cache-models

brucemacd/runner-completion

jmorganca/llama-update-6

brucemacd/benchmark-list

brucemacd/partial-read-caps

parth/deepseek-r1-tools

mxyng/omit-array

parth/tool-prefix-temp

brucemacd/runner-test

jmorganca/qwen25vl

brucemacd/model-forward-test-ext

parth/python-function-parsing

jmorganca/cuda-compression-none

drifkin/num-parallel

drifkin/chat-truncation-fix

jmorganca/sync

parth/python-tools-calling

drifkin/array-head-count

brucemacd/create-no-loop

parth/server-enable-content-stream-with-tools

qwen25omni

mxyng/v3

brucemacd/ropeconfig

jmorganca/silence-tokenizer

parth/sample-so-test

parth/sampling-structured-outputs

brucemacd/doc-go-engine

parth/constrained-sampling-json

jmorganca/mistral-wip

brucemacd/mistral-small-convert

parth/sample-unmarshal-json-for-params

brucemacd/jomorganca/mistral

pdevine/bfloat16

jmorganca/mistral

brucemacd/mistral

pdevine/logging

parth/sample-correctness-fix

parth/sample-fix-sorting

jmorgan/sample-fix-sorting-extras

jmorganca/temp-0-images

brucemacd/parallel-embed-models

brucemacd/shim-grammar

jmorganca/fix-gguf-error

bmizerany/nameswork

jmorganca/faster-releases

bmizerany/validatenames

brucemacd/err-no-vocab

brucemacd/rope-config

brucemacd/err-hint

brucemacd/qwen2_5

brucemacd/logprobs

brucemacd/new_runner_graph_bench

progress-flicker

brucemacd/forward-test

brucemacd/go_qwen2

pdevine/gemma2

jmorganca/add-missing-symlink-eval

mxyng/next-debug

parth/set-context-size-openai

brucemacd/next-bpe-bench

brucemacd/next-bpe-test

brucemacd/new_runner_e2e

brucemacd/new_runner_qwen2

pdevine/convert-cohere2

brucemacd/convert-cli

parth/log-probs

mxyng/next-mlx

mxyng/cmd-history

parth/templating

parth/tokenize-detokenize

brucemacd/check-key-register

bmizerany/grammar

jmorganca/vendor-081b29bd

mxyng/func-checks

jmorganca/fix-null-format

parth/fix-default-to-warn-json

jmorganca/qwen2vl

jmorganca/no-concat

parth/cmd-cleanup-SO

brucemacd/check-key-register-structured-err

parth/openai-stream-usage

parth/fix-referencing-so

stream-tools-stop

jmorganca/degin-1

brucemacd/install-path-clean

brucemacd/push-name-validation

brucemacd/browser-key-register

jmorganca/openai-fix-first-message

jmorganca/fix-proxy

jessegross/sample

parth/disallow-streaming-tools

dhiltgen/remove_submodule

jmorganca/ga

jmorganca/mllama

pdevine/newlines

pdevine/geems-2b

jmorganca/llama-bump

mxyng/modelname-7

mxyng/gin-slog

mxyng/modelname-6

jyan/convert-prog

jyan/quant5

paligemma-support

pdevine/import-docs

jmorganca/openai-context

jyan/paligemma

jyan/p2

jyan/palitest

bmizerany/embedspeedup

jmorganca/llama-vit

brucemacd/allow-ollama

royh/ep-methods

royh/whisper

mxyng/api-models

mxyng/fix-memory

jyan/q4_4/8

jyan/ollama-v

royh/stream-tools

roy-embed-parallel

bmizerany/hrm

revert-5963-revert-5924-mxyng/llama3.1-rope

royh/embed-viz

jyan/local2

jyan/auth

jyan/local

jyan/parse-temp

jmorganca/template-mistral

jyan/reord-g

royh-openai-suffixdocs

royh-imgembed

royh-embed-parallel

jyan/quant4

royh-precision

jyan/progress

pdevine/fix-template

jyan/quant3

pdevine/ggla

mxyng/update-registry-domain

jmorganca/ggml-static

mxyng/create-context

jyan/v0.146

mxyng/layers-from-files

build_dist

bmizerany/noseek

royh-ls

royh-name

timeout

mxyng/server-timestamp

bmizerany/nosillyggufslurps

royh-params

jmorganca/llama-cpp-7c26775

royh-openai-delete

royh-show-rigid

jmorganca/enable-fa

jmorganca/no-error-template

jyan/format

royh-testdelete

bmizerany/fastverify

language_support

pdevine/ps-glitches

brucemacd/tokenize

bruce/iq-quants

bmizerany/filepathwithcoloninhost

mxyng/split-bin

bmizerany/client-registry

jmorganca/if-none-match

native

jmorganca/native

jmorganca/batch-embeddings

jmorganca/initcmake

jmorganca/mm

pdevine/showggmlinfo

modenameenforcealphanum

bmizerany/modenameenforcealphanum

jmorganca/done-reason

jmorganca/llama-cpp-8960fe8

ollama.com

bmizerany/filepathnobuild

bmizerany/types/model/defaultfix

rmdisplaylong

nogogen

bmizerany/x

modelfile-readme

bmizerany/replacecolon

jmorganca/limit

jmorganca/execstack

jmorganca/replace-assets

mxyng/tune-concurrency

jmorganca/testing

whitespace-detection

jmorganca/options

upgrade-all

scratch

cuda-search

mattw/airenamer

mattw/allmodelsonhuggingface

mattw/quantcontext

mattw/whatneedstorun

brucemacd/llama-mem-calc

mattw/faq-context

mattw/communitylinks

mattw/noprune

mattw/python-functioncalling

rename

mxyng/install

pulse

remove-first

editor

mattw/selfqueryingretrieval

cgo

mattw/howtoquant

api

matt/streamingapi

format-config

mxyng/extra-args

shell

update-nous-hermes

cp-model

upload-progress

fix-unknown-model

fix-model-names

delete-fix

insecure-registry

ls

deletemodels

progressbar

readme-updates

license-layers

skip-list

list-models

modelpath

matt/examplemodelfiles

distribution

go-opts

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: github-starred/ollama#29516