Contributors › Luce-Org's local-LLM benchmark configs
Luce-Org's local-LLM benchmark configs
Every tracked benchmark config measured by Luce-Org: 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 · 2885 stars · 34.6 tok/s best single-stream · Luce-Org on github.
Configs measured by Luce-Org
| Model | Hardware | Quant | Backend | Decode | Context | Trust | Source |
|---|---|---|---|---|---|---|---|
| Ling-3.0-Flash-124B-A5.1B | DGX Spark | Q4_K_M | lucebox | 34.6 tok/s | Extracted, source-linked | source |
More: all configs · hardware · news · contributors · methodology · llms.txt · llms-full.txt · API (OpenAPI) · JSON snapshot. Built by Altronis, private on-prem AI, Singapore.