Contributors › EasiiX's local-LLM benchmark configs

EasiiX's local-LLM benchmark configs

Every tracked benchmark config measured by EasiiX: 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.

2 configs · 1 models · 35.7 tok/s best single-stream · EasiiX on huggingface.

Configs measured by EasiiX

ModelQuantBackendDecodeContextTrustSource
Qwen3.8-Flash-NextIQ3_XXSllama.cpp35.7 tok/s156000Extracted, source-linkedsource
Qwen3.8-Flash-NextIQ3_XXSllama.cpp23.5 tok/s156000Extracted, source-linkedsource

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