DISCOVER BY GPU

Setups running on
Mac M3 Max.

Every published setup that reports this GPU, with its models, quantization, runtime and reported results. Use the directory filters below to narrow by capacity, model or runtime.

1documented use
on this GPU

Capacity range

Exact reported VRAM

Practice

Model

Quantization

Context length

Reported speed

Runtime

Tools / workflow (harness)

Record origin

EXPLORE BY CAPACITY

Start with your machine.

Capacity is the reported total for this setup. Multi-GPU and unified-memory layouts can behave differently.

8 GB or lessLaptops, iGPUs and modest cards 9–12 GBEntry-level local inference 13–16 GBCurrent mid-range cards 17–20 GBRX 7900 XT and compact pro cards 21–24 GB3090, 4090 and 7900 XTX class 25–32 GB5090 and workstation cards 33–48 GBWorkstation and multi-GPU setups 49–96 GBLarge multi-GPU and datacenter setups 97 GB+Unified memory, servers and clusters

1 resultsEvery record keeps its origin visible.

Hybrid orchestrationGenesis archive2026-09

Hybrid RAG and cybersecurity work across two Macs

A privacy-focused workflow combines local models on an M2 Ultra and M3 Max with GCP and OpenRouter for RAG and security work.

Qwen 3.8 27B Mac M2 Ultra

Hybrid↑ 3