Can I run SmolLM3 3B?

chatgeneralreasoning · sizes: 3B

What runs it

machinebest fitverdictspeed
Apple M1 · 8GB 3B Q4_K_M ✅ Runs (tight) 20–35 tok/s
Apple M1 Pro · 16GB 3B Q8_0 ✅ Runs comfortably 35–55 tok/s
Apple M2 · 16GB 3B Q8_0 ✅ Runs comfortably 19–30 tok/s
Apple M3 Pro · 18GB 3B Q8_0 ✅ Runs comfortably 25–45 tok/s
Apple M2 Pro · 32GB 3B Q8_0 ✅ Runs comfortably 35–55 tok/s
Apple M4 Pro · 48GB 3B Q8_0 ✅ Runs comfortably 45–75 tok/s
Apple M3 Max · 36GB 3B Q8_0 ✅ Runs comfortably 55–95 tok/s
Apple M2 Max · 64GB 3B Q8_0 ✅ Runs comfortably 55–95 tok/s
Apple M4 Max · 128GB 3B Q8_0 ✅ Runs comfortably 70–120 tok/s
Apple M2 Ultra · 192GB 3B Q8_0 ✅ Runs comfortably 100–170 tok/s
NVIDIA GeForce RTX 3060 · 12GB VRAM 3B Q8_0 ✅ Runs comfortably 45–80 tok/s
NVIDIA GeForce RTX 4070 · 12GB VRAM 3B Q8_0 ✅ Runs comfortably 65–110 tok/s
NVIDIA GeForce RTX 4090 · 24GB VRAM 3B Q8_0 ✅ Runs comfortably 130–220 tok/s
NVIDIA GeForce RTX 5080 · 16GB VRAM 3B Q8_0 ✅ Runs comfortably 130–210 tok/s
NVIDIA GeForce RTX 5090 · 32GB VRAM 3B Q8_0 ✅ Runs comfortably 240–390 tok/s
AMD Radeon RX 7900 XTX · 24GB VRAM 3B Q8_0 ✅ Runs comfortably 120–200 tok/s

Shopping for a machine? What hardware do I need to run SmolLM3 3B? →

Check your exact rig: open the checker →

$npx runlocal-sh can-i-run smollm3

Architectural kin

8 models share SmolLM3 3B's KV-cache geometry — they size memory the same way, so a rig that fits one tends to fit its same-size kin.

Explore the whole catalog by architecture: open the graph →