Contributors › Plaaasma's local-LLM benchmark configs

Plaaasma's local-LLM benchmark configs

Every tracked benchmark config measured by Plaaasma: model, quant, backend, tokens per second, source-linked and trust-tiered.

Snapshot 2026-10-15 · 394 configs on AI boxes and 423 on GPU cards · 123 models. Every number is generated from the tracker snapshot and linked to where it was measured; nothing here is typed by hand.

1 configs · 1 models · 100.1 tok/s best single-stream · Plaaasma on github.

Configs measured by Plaaasma

No single-stream configs recorded yet.

More: all configs · hardware · news · contributors · methodology · llms.txt · llms-full.txt · API (OpenAPI) · JSON snapshot. Built by Altronis, private on-prem AI, Singapore.