# Local LLM Hardware Statistics (2026)

> As of September 10, 2026, BenchLM documents license, quantization, and reference hardware for 12 ranked open-weight models. Updated September 10, 2026; every number regenerates from BenchLM's live dataset on each data refresh.

## Key statistics

- As of September 10, 2026, BenchLM documents license, quantization, and reference hardware for 12 ranked open-weight models.
- As of September 10, 2026, 2 of the 12 ranked local-model receipts on BenchLM use one 24GB NVIDIA RTX 4090 as the reference configuration.
- As of September 10, 2026, Google's Gemma 4 31B is the highest-scoring model in BenchLM's documented single-GPU subset at 52.6/100, with a 24GB RTX 4090 reference setup.
- As of September 10, 2026, 6 of 12 ranked models in BenchLM's deployment subset (50%) use an OSI-approved license.

## Methodology

This page joins the current ranked open-weight cohort to BenchLM's reviewed self-host catalog, last checked 2026-06-12. A “single-GPU” row has a documented reference configuration using at most 32GB of GPU or unified memory. These receipts are deployment examples, not a claim that every runtime, quantization, or context length will fit.

## FAQ

### How many ranked local LLMs fit on one 24GB GPU?

As of September 10, 2026, 2 of the 12 ranked models with reviewed deployment receipts use one 24GB RTX 4090 as their reference setup. This count covers the documented quantization and configuration only; longer contexts and different runtimes can require more memory.

### What is the highest-scoring LLM documented for one GPU?

As of September 10, 2026, Google's Gemma 4 31B leads BenchLM's documented single-GPU subset at 52.6/100. Its reference row uses one 24GB RTX 4090. The score measures benchmark capability, not local throughput, latency, or the quality loss from a specific quantization.

### Does open-weight mean open source?

No. As of September 10, 2026, 6 of 12 ranked models in BenchLM's deployment subset use an OSI-approved license. “Open-weight” only means the weights are downloadable; community and custom licenses can restrict commercial use, redistribution, or derived models.

## Sources

- [Open-weight deployment directory](https://benchlm.ai/best/open-source#deployment-directory)
- [Local LLM rankings](https://benchlm.ai/best/local-llm)
- [LLM VRAM calculator](https://benchlm.ai/tools/llm-vram-calculator)
- [Self-hosting cost calculator](https://benchlm.ai/tools/self-host-calculator)

Cite as: BenchLM.ai, "LLM Statistics" (September 10, 2026), https://benchlm.ai/stats/local-llm-hardware

Canonical page: https://benchlm.ai/stats/local-llm-hardware