| by gpu tier | Q2_K 12.8 GB | Q4_K_M 17.0 GB | Q5_K_M 21.3 GB | Q6_K 25.5 GB | Q8_0 34.0 GB | FP16 68.0 GB |
|---|---|---|---|---|---|---|
| 8 GB tier rtx 3050 · 4060 | ||||||
| 12 GB tier rtx 3060 · 4070 | ||||||
| 16 GB tier rtx 4080 · 4060 ti 16g | OK 43 t/s | |||||
| 24 GB tier rtx 3090 · 4090 | GREAT 70 t/s | GREAT 53 t/s | TIGHT 43 t/s | |||
| 32 GB tier rtx 5090 · m3 max | GREAT 130 t/s | GREAT 98 t/s | GREAT 79 t/s | OK 66 t/s | ||
| 48 GB tier a6000 · m3 max 64 | GREAT 42 t/s | GREAT 32 t/s | GREAT 25 t/s | GREAT 21 t/s | GREAT 16 t/s | |
| 80 GB tier h100 · m3 ultra 128 | GREAT 142 t/s | GREAT 107 t/s | GREAT 86 t/s | GREAT 72 t/s | GREAT 54 t/s | OK 27 t/s |