70B that rivals far larger models. The best open general model that fits a 64GB Mac.
chatgeneralreasoningagents · sizes: 70B · Llama 3.3 Community
| machine | best fit | verdict | speed |
|---|---|---|---|
| Apple M1 · 8GB | 70B Q2_K | ❌ Won't fit | — |
| Apple M1 Pro · 16GB | 70B Q2_K | ❌ Won't fit | — |
| Apple M2 · 16GB | 70B Q2_K | ❌ Won't fit | — |
| Apple M3 Pro · 18GB | 70B Q2_K | ❌ Won't fit | — |
| Apple M2 Pro · 32GB | 70B Q2_K | 🐢 CPU-only (slow) | 0.5–0.8 tok/s |
| Apple M4 Pro · 48GB | 70B Q2_K | ✅ Runs (tight) | 5–8 tok/s |
| Apple M3 Max · 36GB | 70B Q2_K | 🐢 CPU-only (slow) | 0.8–1 tok/s |
| Apple M2 Max · 64GB | 70B Q4_K_M | ✅ Runs (tight) | 4–7 tok/s |
| Apple M4 Max · 128GB | 70B Q8_0 | ✅ Runs (tight) | 3–5 tok/s |
| Apple M2 Ultra · 192GB | 70B Q8_0 | ✅ Runs comfortably | 3–5 tok/s |
| NVIDIA GeForce RTX 3060 · 12GB VRAM | 70B Q2_K | ❌ Won't fit | — |
| NVIDIA GeForce RTX 4070 · 12GB VRAM | 70B Q2_K | ❌ Won't fit | — |
| NVIDIA GeForce RTX 4090 · 24GB VRAM | 70B Q2_K | ⚠️ Partial GPU offload | 5–8 tok/s |
| NVIDIA GeForce RTX 5080 · 16GB VRAM | 70B Q2_K | ❌ Won't fit | — |
| NVIDIA GeForce RTX 5090 · 32GB VRAM | 70B Q2_K | ✅ Runs (tight) | 25–40 tok/s |
| AMD Radeon RX 7900 XTX · 24GB VRAM | 70B Q2_K | ⚠️ Partial GPU offload | 4–7 tok/s |
Shopping for a machine? What hardware do I need to run Llama 3.3? →
Check your exact rig: open the checker →
19 models share Llama 3.3's KV-cache geometry — they size memory the same way, so a rig that fits one tends to fit its same-size kin.
…and 7 more.
Explore the whole catalog by architecture: open the graph →