Self Hosted

7 items tagged with "self-hosted"

Filter by type:

Models2

Gemma 4 26B A4B IT

An instruction-tuned Gemma 4 model listed on OpenRouter, positioned as a large open model for general-purpose chat and instruction following with a long context window.

Model

Llama 3.3 70B

Open-weight multilingual model matching Llama 3.1 405B performance

Stacks1

Stack

Jenkins + Nexus

A self-hosted CI and artifact-management stack pairing Jenkins automation pipelines with Sonatype Nexus as a binary repository for builds and dependencies.

Comparisons4

Comparison

Open-Weight vs Proprietary LLMs

Open-weight models can be downloaded and self-hosted; proprietary models are accessed via API. The split shapes control, cost, privacy, and capability ceilings.

Comparison

vLLM vs TGI

vLLM and Hugging Face Text Generation Inference (TGI) are high-throughput LLM serving engines. Both optimize GPU inference but differ in ecosystem and tuning focus.

Comparison

Hugging Face vs OpenAI API

Hugging Face provides open models, tooling, and self-hosting paths; the OpenAI API offers managed access to proprietary models. The choice trades control against convenience.

Comparison

Self-Hosted vs Managed Inference

Self-hosted inference runs models on your own infrastructure; managed inference uses a provider's endpoint. The choice trades control, privacy, and cost-at-scale against simplicity.