StackMap
Subscribe

Ollama vs sie

Run Llama, Mistral and other open models locally with a single command and a clean API. — versus — Self-hosted inference cluster for everything agents call besides the big LLM: embeddings, rerankers, OCR, NER, guardrails and small LLMs — 100+ models, one OpenAI-compatible API, K8s stack included.

The curated verdict

Same 'serve open models behind one local API' job at different scales: Ollama is the single-machine developer runner; SIE is the multi-model production cluster with autoscaling, gateway and Terraform.

Ollamasie
Stars176k2.2k
Forks17k200
LanguageGoPython
LicenseMITApache-2.0
Last activitytodayyesterday
Topicslocallocal, rag
Curated connections163

Ollama — the curator's take

Run Llama, Mistral and other open models locally with a single command and a clean API.

sie — the curator's take

Fills the gap between 'vLLM serves my big model' and the pile of task models agents actually need: retrieval (bge-m3, SPLADE, ColBERT), doc-to-markdown (MinerU, GLM-OCR, docling), structured extraction (GLiNER), safety verdicts (Granite Guardian) — one cluster, on-demand loading with LRU eviction instead of a server per model. The production story is unusually complete and all Apache-2.0: load-balancing gateway, KEDA scale-to-zero, Grafana dashboards, Terraform for GKE/EKS/AKS; the MCP edge offloads document work from Claude-class clients to your cluster. NOT for max-throughput single-LLM serving — that stays vLLM/SGLang territory (SIE's own generation image wraps SGLang). Telemetry is on by default, opt-out env var.