{"id":16179209,"url":"https://github.com/jonashackt/ollama-linux","last_synced_at":"2026-01-21T16:32:11.458Z","repository":{"id":252372420,"uuid":"840233119","full_name":"jonashackt/ollama-linux","owner":"jonashackt","description":"Just some exploration on how to use Ollama on Linx","archived":false,"fork":false,"pushed_at":"2024-08-14T06:52:17.000Z","size":9,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-02-13T14:23:38.438Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/jonashackt.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-08-09T08:54:47.000Z","updated_at":"2024-08-14T06:52:20.000Z","dependencies_parsed_at":"2024-10-10T05:33:27.617Z","dependency_job_id":"c4025189-4631-4be9-ab17-d089b88cbf0b","html_url":"https://github.com/jonashackt/ollama-linux","commit_stats":null,"previous_names":["jonashackt/ollama-linux"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jonashackt%2Follama-linux","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jonashackt%2Follama-linux/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jonashackt%2Follama-linux/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jonashackt%2Follama-linux/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/jonashackt","download_url":"https://codeload.github.com/jonashackt/ollama-linux/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247648923,"owners_count":20972942,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2024-10-10T05:25:59.142Z","updated_at":"2026-01-21T16:32:11.405Z","avatar_url":"https://github.com/jonashackt.png","language":null,"funding_links":[],"categories":[],"sub_categories":[],"readme":"# ollama-linux\nJust some exploration on how to use Ollama on Linx\n\n\n# Why Ollama on Linux\n\nI do already have a Thinkpad P1 Gen 6 incl. a dGPU (Nvidia Geforce 4060) running with Manjaro Linux - but I'm thinking about getting another machine from Tuxedo for some reasons.\n\nI did the switch to Linux for various reasons (see this repo for more info: https://github.com/jonashackt/mac-to-linux).\n\nNow I have the question if I can run local LLMs also on non-Nvidia, non-Windows/Mac Laptops.\n\n\n# Ollama on AMD\n\nIn March 2024 there was already a post that Ollama now supports AMD grafics cards: https://ollama.com/blog/amd-preview \n\nBut these are dGPUs or desktop-grade cards. What about the promising Ryzen iGPU variants?\n\n\n## Ollama on AMD iGPUs (Ryzen AI)\n\nThere is ongoing work at the moment to support iGPUs also. See https://github.com/ollama/ollama/issues/5186 \n\nAlso there are examples of already running models on iGPUs https://blog.machinezoo.com/Running_Ollama_on_AMD_iGPU, but without the UMA/GART/GTT support that is currently under way like it seems, if I understand https://github.com/ollama/ollama/issues/2637 correctly.\n\n\u003e GTT stands for graphics translation table or graphics address remapping table (GART) https://en.wikipedia.org/wiki/Graphics_address_remapping_table and can be used to address the systems RAM from the iGPU (which theoretically let's the iGPU access e.g. \u003c96GB of RAM in a laptop for the LLM)\n\nJust 2 days ago https://github.com/ollama/ollama/issues/2637#issuecomment-2272913656 there were already really promising results reported. \n\nIt is important to have Linux Kernel 6.10 running, as stated in https://www.phoronix.com/news/Linux-6.10-AMDKFD-Small-APUs\n\nCurrently on my Thinkpad I have Manjaro running Kernel 6.6, but 6.10 is available...\n\n\n# Links\n\nhttps://www.youtube.com/watch?v=h34vA2bkbtk\n\n\n## eGPU\n\nhttps://www.notebookcheck.com/MateBook-GT-14-OLED-Notebook-startet-auch-mit-Intel-Core-Ultra-9-und-unterstuetzt-externe-Grafikkarten.873504.0.html\nhttps://www.notebookcheck.com/Huawei-Hi-GT-Cube-Kompakte-externe-Grafikkarte-startet-mit-Einschraenkungen.870875.0.html\n\nhttps://www.notebookcheck.com/GPD-G1-eGPU-im-Test-Externe-AMD-Radeon-RX-7600M-XT-mit-8-GB-VRAM-nutzt-USB-4-0-oder-OCuLink.775468.0.html\n\nhttps://www.igorslab.de/der-grosse-egpu-guide-und-benchmark-test-was-taugt-eine-extern-betriebene-grafikkarte-nvidia-oder-amd-wer-kommt-besser-damit-klar/6/\n\nhttps://egpu.de/razer-core-x/\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjonashackt%2Follama-linux","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjonashackt%2Follama-linux","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjonashackt%2Follama-linux/lists"}