Contributors › theNetworkChuck's local-LLM benchmark configs

theNetworkChuck's local-LLM benchmark configs

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

Snapshot 2026-09-30 · 254 configs · 116 models. Every number is generated from the tracker snapshot and linked to where it was measured; nothing here is typed by hand.

3 configs · 3 models · 7 stars · 109.1 tok/s best single-stream · theNetworkChuck on github.

Configs measured by theNetworkChuck

ModelQuantBackendDecodeContextTrustSource
Qwen3.6 35B-A3BMLX-4BITmlx109.1 tok/s (prefill 6012)32000Extracted, source-linkedsource
Qwen3 14BMLX-4BITmlx55.4 tok/s (prefill 2278)32000Extracted, source-linkedsource
Qwen3.8 27BMLX-4BITmlx42.6 tok/s (prefill 1526)32000Extracted, source-linkedsource

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