Contributors › piotreknow02's local-LLM benchmark configs
piotreknow02's local-LLM benchmark configs
Every tracked benchmark config measured by piotreknow02: 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 · 1 stars · 29 tok/s best single-stream · piotreknow02 on github.
Configs measured by piotreknow02
| Model | Hardware | Quant | Backend | Decode | Context | Trust | Source |
|---|---|---|---|---|---|---|---|
| GLM-5.3-Flash | Strix Halo | exllamav3 (speculative decode, mtp-2) | 29 tok/s (prefill 580) | 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.