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
| Model | Quant | Backend | Decode | Context | Trust | Source |
|---|---|---|---|---|---|---|
| Qwen3.8-Flash-Next | Q4_K_XL | llama.cpp/vulkan | 24 tok/s | Extracted, source-linked | source |
More: all configs · hardware · methodology · llms.txt · llms-full.txt · API (OpenAPI) · JSON snapshot. Built by Altronis, private on-prem AI, Singapore.