LiveBench
instruction following80.6
coding70.3
language49.4
overall66.8
| by gpu tier | Q2_K 251.6 GB | Q4_K_M 335.5 GB | Q5_K_M 419.4 GB | Q6_K 503.3 GB | Q8_0 671.0 GB | FP16 1342.0 GB |
|---|
| 8 GB tier rtx 3050 · 4060 | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ |
| 12 GB tier rtx 3060 · 4070 | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ |
| 16 GB tier rtx 4080 · 4060 ti 16g | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ |
| 24 GB tier rtx 3090 · 4090 | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ |
| 32 GB tier rtx 5090 · m3 max | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ |
| 48 GB tier a6000 · m3 max 64 | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ |
| 80 GB tier h100 · m3 ultra 128 | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ |
full fit · production speed tight fit · usabledoesn't fit
Get personalized ranking
Tell us your machine — we'll tell you if this is actually your best pick, or what's better.
Rank for my hardware