What hardware runs QwQ 32B?

The cheapest cataloged machine that runs QwQ 32B on the GPU is a AMD Radeon RX 7900 XTX · 24GB VRAM. Here are the most affordable rigs that fit it, smallest memory first.

machinebest fitverdictspeed
AMD Radeon RX 7900 XTX · 24GB VRAM 32B Q4_K_M ✅ Runs (tight) 17–30 tok/s
NVIDIA GeForce RTX 3090 · 24GB VRAM 32B Q4_K_M ✅ Runs (tight) 18–30 tok/s
NVIDIA GeForce RTX 4090 · 24GB VRAM 32B Q4_K_M ✅ Runs (tight) 19–30 tok/s
NVIDIA GeForce RTX 5090 · 32GB VRAM 32B Q5_K_M ✅ Runs (tight) 30–50 tok/s
Apple M3 Max · 48GB 32B Q5_K_M ✅ Runs comfortably 7–12 tok/s
Apple M4 Max · 48GB 32B Q5_K_M ✅ Runs comfortably 9–16 tok/s
Apple M4 Pro · 48GB 32B Q5_K_M ✅ Runs comfortably 6–10 tok/s
AMD Radeon Pro W7900 · 48GB VRAM 32B Q8_0 ✅ Runs (tight) 9–15 tok/s
Apple M1 Max · 64GB 32B Q8_0 ✅ Runs (tight) 5–8 tok/s
Apple M1 Ultra · 64GB 32B Q8_0 ✅ Runs (tight) 6–11 tok/s
Apple M2 Max · 64GB 32B Q8_0 ✅ Runs (tight) 5–8 tok/s
Apple M2 Ultra · 64GB 32B Q8_0 ✅ Runs (tight) 6–11 tok/s

Already have a machine? See QwQ 32B across popular rigs → or check your exact rig →

Planning a whole workflow? Rigs for a coding agent · local chat · reasoning · local RAG setup.

$npx runlocal-sh can-i-run qwq --hardware <your-rig>

Verdicts use the same GQA-aware fit math as the CLI — a AMD Radeon RX 7900 XTX verdict here matches what runlocal tells you on the machine.