What is the fastest local LLM hardware under 60 W?

Name: What is the fastest local LLM hardware under 60 W?
Creator: HWBench

Intel 13900K (Nvidia 5090) (as tested by Jeff Geerling): 271 tok/s (Llama 3.2:3b, as in linked issue (Ollama default tags are 4-bit); grade D; undated). Next: Intel Core Ultra 7 368H 250 tok/s; Ryzen 9 7900X (Nvidia 4090) (as tested by Jeff Geerling) 237 tok/s. Like-for-like group: LLM ≤4B, batch 1.

Top results
#	Platform	Result	Perf/W	Price	Grade · date	Source
1	Intel 13900K (Nvidia 5090) (as tested by Jeff Geerling)	271 tok/s Llama 3.2:3b · as in linked issue (Ollama default tags are 4-bit)	unknown	unknown	D undated	Jeff Geerling ai-benchmarks README (Findings tables)
2	Intel Core Ultra 7 368H	250 tok/s minicpm4-0.5b · INT4-MIXED	unknown	unknown	D undated	OpenVINO official LLM benchmarks (llm_models_7-368H.csv)
3	Ryzen 9 7900X (Nvidia 4090) (as tested by Jeff Geerling)	237 tok/s Llama 3.2:3b · as in linked issue (Ollama default tags are 4-bit)	unknown	unknown	D undated	Jeff Geerling ai-benchmarks README (Findings tables)
4	Intel 13900K (Nvidia 4090) (as tested by Jeff Geerling)	216 tok/s Llama 3.2:3b · as in linked issue (Ollama default tags are 4-bit)	unknown	unknown	D undated	Jeff Geerling ai-benchmarks README (Findings tables)
5	Ryzen 9 7950X (Nvidia 4080) (as tested by Jeff Geerling)	204 tok/s Llama 3.2:3b · as in linked issue (Ollama default tags are 4-bit)	unknown	unknown	D undated	Jeff Geerling ai-benchmarks README (Findings tables)

Filters: task=LLM generation, power=60. Ranking: boards that meet every known target, then headroom and perf/W; unknown power or price is not penalised. Open in /find · JSON

Sources

Generated 2026-10-16 from HWBench data only. All answers · Submit a result

Machine-readable: /find.json (see llms.txt); full tables are in “Show data”. Confidence grades: A audited MLPerf closed · B documented third-party · C community · D vendor-published · E estimate. Unknown values are shown as unknown, never estimated. Generated 2026-10-16 from public sources.