Contributors › sypherin's local-LLM benchmark configs

sypherin's local-LLM benchmark configs

Every tracked benchmark config measured by sypherin: 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.

4 configs · 3 models · 73 stars · 66 tok/s best single-stream · sypherin on github.

Configs measured by sypherin

ModelQuantBackendDecodeContextTrustSource
Qwen3.6-35B-A3B-MTPUD-Q4_K_XLvulkan66 tok/s262144Verified (ran it)source
Qwen3.6-35B-A3BUD-Q8_K_XLllama.cpp/vulkan41 tok/sVerified (ran it)source
Qwen3.6-35B-A3BUD-Q8_K_XLllama.cpp/rocm39 tok/sVerified (ran it)source
Qwen3.8-27BUD-Q4_K_XLllama.cpp/vulkan24.6 tok/s131072Verified (ran it)source

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