Contributors › kingjones777's local-LLM benchmark configs
kingjones777's local-LLM benchmark configs
Every tracked benchmark config measured by kingjones777: 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 · 20.3 tok/s best single-stream · kingjones777 on huggingface.
Configs measured by kingjones777
| Model | Hardware | Quant | Backend | Decode | Context | Trust | Source |
|---|---|---|---|---|---|---|---|
| Muse-Glimmer-30B | Strix Halo | FP4 | llama.cpp (speculative decode, dflash) | 20.3 tok/s | 32768 | 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.