Can I run OLMo 2 7B?

chatgeneral · sizes: 7B

What runs it

machinebest fitverdictspeed
Apple M1 · 8GB 7B Q4_K_M ❌ Won't fit —
Apple M1 Pro · 16GB 7B Q8_0 🐢 CPU-only (slow) 1–2 tok/s
Apple M2 · 16GB 7B Q8_0 🐢 CPU-only (slow) 0.6–1 tok/s
Apple M3 Pro · 18GB 7B Q4_K_M ✅ Runs (tight) 10–16 tok/s
Apple M2 Pro · 32GB 7B Q8_0 ✅ Runs comfortably 9–16 tok/s
Apple M4 Pro · 48GB 7B Q8_0 ✅ Runs comfortably 12–20 tok/s
Apple M3 Max · 36GB 7B Q8_0 ✅ Runs comfortably 16–25 tok/s
Apple M2 Max · 64GB 7B Q8_0 ✅ Runs comfortably 16–25 tok/s
Apple M4 Max · 128GB 7B Q8_0 ✅ Runs comfortably 20–35 tok/s
Apple M2 Ultra · 192GB 7B Q8_0 ✅ Runs comfortably 20–35 tok/s
NVIDIA GeForce RTX 3060 · 12GB VRAM 7B Q6_K ✅ Runs (tight) 14–25 tok/s
NVIDIA GeForce RTX 4070 · 12GB VRAM 7B Q6_K ✅ Runs (tight) 20–35 tok/s
NVIDIA GeForce RTX 4090 · 24GB VRAM 7B Q8_0 ✅ Runs comfortably 35–60 tok/s
NVIDIA GeForce RTX 5080 · 16GB VRAM 7B Q8_0 ✅ Runs (tight) 35–55 tok/s
NVIDIA GeForce RTX 5090 · 32GB VRAM 7B Q8_0 ✅ Runs comfortably 65–110 tok/s
AMD Radeon RX 7900 XTX · 24GB VRAM 7B Q8_0 ✅ Runs comfortably 35–55 tok/s

Shopping for a machine? What hardware do I need to run OLMo 2 7B? →

Check your exact rig: open the checker →

$npx runlocal-sh can-i-run olmo2

Architectural kin

2 models share OLMo 2 7B's KV-cache geometry — they size memory the same way, so a rig that fits one tends to fit its same-size kin.

Code Llama
shares 32kv/128hd
LLaVA
shares 32kv/128hd

Explore the whole catalog by architecture: open the graph →