Contributors › routhjim's local-LLM benchmark configs

routhjim's local-LLM benchmark configs

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

Snapshot 2026-09-10 · 148 configs · 69 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 · 24 tok/s best single-stream · routhjim on github.

Configs measured by routhjim

ModelQuantBackendDecodeContextTrustSource
Qwen3.8-Flash-NextQ4_K_XLllama.cpp/vulkan24 tok/sExtracted, source-linkedsource

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