Contributors › nabe2030's local-LLM benchmark configs
nabe2030's local-LLM benchmark configs
Every tracked benchmark config measured by nabe2030: model, quant, backend, tokens per second, source-linked and trust-tiered.
Snapshot 2026-10-29 · 413 configs on AI boxes and 288 on GPU cards · 121 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 · 10.7 tok/s best single-stream · nabe2030 on github.
Configs measured by nabe2030
| Model | Hardware | Quant | Backend | Decode | Context | Trust | Source |
|---|---|---|---|---|---|---|---|
| Gemma-4-31B-IT | DGX Spark | Q4_K_M | llama.cpp/cuda | 10.7 tok/s (prefill 746.3) | Structured table | 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.