Run an open-weight model on your own infrastructure
Download and self-host a model's weights on the buyer's own servers or cloud account, rather than call a vendor-hosted API. 37 products across 24 companies in the Ludbee catalogue carry this task — spanning every layer of the stack that exists here, not one of its own: 5 Application, 5 Infrastructure, 5 Foundation Models, 9 Hardware.
Filter the whole directory by this job to sort and compare these products.
Where these run
- Self-hosted
- 36 of 37 products that record it
- On-device
- 7 of 37 products that record it
- SaaS
- 7 of 37 products that record it
- Hybrid
- 5 of 37 products that record it
- Private cloud
- 4 of 37 products that record it
- Air-gapped
- 2 of 37 products that record it
One product can run more than one way — the counts above are of records, not of products.
What this page does not claim
This list carries no score and no recommendation, and one order only: inside each layer, a company whose product for this task is marked AI feature — sold for another job, with AI as one function its own page names — comes after the rest, A–Z within each. The standing rule that applies to the whole directory applies here too: no payment changes a figure, a ranking or the order of any list, this one included. Nor can it yet say what governs any of these products once deployed — what data they can reach, what they are certified against, whether a vendor trains on what you send it. That field is defined in the ontology and is populated on none of the 3,888 products in the catalogue yet, so a page that leaned on it would be promising an answer the data cannot back. It will say so here the day that changes.
The companies
Application (5)
- GitLab — GitLab Duo Agent Platform Self-Hosted
- Linagora — Lucie-7B
- LM Studio — llmster, LM Link
- M42 — Med42
- Siemens — Industrial AI Suite
Infrastructure (5)
Foundation Models (5)
- Alibaba — ModelScope
- Baidu — PaddlePaddle
- Decart — Decart Optimization Stack
- Poolside AI — Poolside Platform
- Sarvam AI — Sarvam Edge
Hardware (9)
- AMD — AMD Enterprise AI Reference Stack, AMD ROCm, AMD Vitis AI
- Dell Technologies — Dell AI Factory with NVIDIA, Dell Enterprise Hub
- Hailo Technologies — Hailo AI Software Suite
- Hewlett Packard Enterprise — HPE Private Cloud AI
- Huawei — CANN, MindIE, MindSpore, MindStudio
- Intel — Intel Geti, Intel Neural Compressor, OpenVINO toolkit
- NVIDIA — NVIDIA AI Enterprise, NVIDIA Dynamo-Triton (Triton Inference Server), NVIDIA NIM, NVIDIA TensorRT
- Qualcomm — Qualcomm AI Inference Suite
- Super Micro Computer — Supermicro AI SuperCluster, Supermicro Super AI Station