01.AI's bilingual models, strong at reasoning and code for their size.
chatgeneralreasoning · sizes: 6B, 9B, 34B · Apache-2.0
| machine | best fit | verdict | speed |
|---|---|---|---|
| Apple M1 · 8GB | 9B Q5_K_M | 🐢 CPU-only (slow) | 0.7–1 tok/s |
| Apple M1 Pro · 16GB | 9B Q5_K_M | ✅ Runs (tight) | 15–25 tok/s |
| Apple M2 · 16GB | 9B Q5_K_M | ✅ Runs (tight) | 8–14 tok/s |
| Apple M3 Pro · 18GB | 9B Q5_K_M | ✅ Runs comfortably | 12–20 tok/s |
| Apple M2 Pro · 32GB | 34B Q3_K_M | ✅ Runs (tight) | 6–9 tok/s |
| Apple M4 Pro · 48GB | 34B Q5_K_M | ✅ Runs comfortably | 5–9 tok/s |
| Apple M3 Max · 36GB | 34B Q3_K_M | ✅ Runs (tight) | 10–16 tok/s |
| Apple M2 Max · 64GB | 34B Q8_0 | ✅ Runs (tight) | 5–8 tok/s |
| Apple M4 Max · 128GB | 34B Q8_0 | ✅ Runs comfortably | 6–10 tok/s |
| Apple M2 Ultra · 192GB | 34B Q8_0 | ✅ Runs comfortably | 7–11 tok/s |
| NVIDIA GeForce RTX 3060 · 12GB VRAM | 9B Q8_0 | ✅ Runs (tight) | 15–25 tok/s |
| NVIDIA GeForce RTX 4070 · 12GB VRAM | 9B Q8_0 | ✅ Runs (tight) | 20–35 tok/s |
| NVIDIA GeForce RTX 4090 · 24GB VRAM | 34B Q3_K_M | ✅ Runs (tight) | 20–35 tok/s |
| NVIDIA GeForce RTX 5080 · 16GB VRAM | 9B Q8_0 | ✅ Runs comfortably | 40–70 tok/s |
| NVIDIA GeForce RTX 5090 · 32GB VRAM | 34B Q5_K_M | ✅ Runs (tight) | 30–45 tok/s |
| AMD Radeon RX 7900 XTX · 24GB VRAM | 34B Q3_K_M | ✅ Runs (tight) | 20–35 tok/s |
Shopping for a machine? What hardware do I need to run Yi 1.5? →
Check your exact rig: open the checker →
23 models share Yi 1.5's KV-cache geometry — they size memory the same way, so a rig that fits one tends to fit its same-size kin.
…and 11 more.
Explore the whole catalog by architecture: open the graph →