| RTX 4060 | 3-bit | 96K | 123 tok/s | 1.0 s | PDF: Mellum2.1 12B A2.5B Thinking on RTX 4060 report |
|---|
| RTX 5060 | 3-bit | 96K | 179 tok/s | 0.8 s | PDF: Mellum2.1 12B A2.5B Thinking on RTX 5060 report |
|---|
| RTX 3070 | 3-bit | 96K | 179 tok/s | 0.8 s | PDF: Mellum2.1 12B A2.5B Thinking on RTX 3070 report |
|---|
| RTX 3080 10 GB | 5-bit | 48K | 199 tok/s | 0.5 s | PDF: Mellum2.1 12B A2.5B Thinking on RTX 3080 10 GB report |
|---|
| RTX 3060 12 GB | 6-bit | 96K | 102 tok/s | 1.2 s | PDF: Mellum2.1 12B A2.5B Thinking on RTX 3060 12 GB report |
|---|
| Arc B580 | 6-bit | 96K | 85 tok/s | 0.8 s | PDF: Mellum2.1 12B A2.5B Thinking on Arc B580 report |
|---|
| RTX 4070 | 6-bit | 96K | 133 tok/s | 0.5 s | PDF: Mellum2.1 12B A2.5B Thinking on RTX 4070 report |
|---|
| RTX 4070 Super | 6-bit | 96K | 133 tok/s | 0.4 s | PDF: Mellum2.1 12B A2.5B Thinking on RTX 4070 Super report |
|---|
| RTX 5070 | 6-bit | 96K | 166 tok/s | 0.5 s | PDF: Mellum2.1 12B A2.5B Thinking on RTX 5070 report |
|---|
| RTX 4060 Ti 16 GB | 8-bit | 128K | 67 tok/s | 0.7 s | PDF: Mellum2.1 12B A2.5B Thinking on RTX 4060 Ti 16 GB report |
|---|
| RTX 5060 Ti 16 GB | 8-bit | 128K | 99 tok/s | 0.7 s | PDF: Mellum2.1 12B A2.5B Thinking on RTX 5060 Ti 16 GB report |
|---|
| Arc A770 16 GB | 8-bit | 128K | 81 tok/s | 0.8 s | PDF: Mellum2.1 12B A2.5B Thinking on Arc A770 16 GB report |
|---|
| Radeon RX 9070 XT | 8-bit | 128K | 106 tok/s | 0.4 s | PDF: Mellum2.1 12B A2.5B Thinking on Radeon RX 9070 XT report |
|---|
| RTX 4070 Ti Super | 8-bit | 128K | 136 tok/s | 0.4 s | PDF: Mellum2.1 12B A2.5B Thinking on RTX 4070 Ti Super report |
|---|
| RTX 4080 Super | 8-bit | 128K | 146 tok/s | 0.3 s | PDF: Mellum2.1 12B A2.5B Thinking on RTX 4080 Super report |
|---|
| RTX 5070 Ti | 8-bit | 128K | 169 tok/s | 0.4 s | PDF: Mellum2.1 12B A2.5B Thinking on RTX 5070 Ti report |
|---|
| RTX 5080 | 8-bit | 128K | 178 tok/s | 0.3 s | PDF: Mellum2.1 12B A2.5B Thinking on RTX 5080 report |
|---|
| Radeon RX 7900 XTX | 8-bit | 128K | 140 tok/s | 0.7 s | PDF: Mellum2.1 12B A2.5B Thinking on Radeon RX 7900 XTX report |
|---|
| RTX 3090 | 8-bit | 128K | 174 tok/s | 0.4 s | PDF: Mellum2.1 12B A2.5B Thinking on RTX 3090 report |
|---|
| RTX 4090 | 8-bit | 128K | 184 tok/s | 0.2 s | PDF: Mellum2.1 12B A2.5B Thinking on RTX 4090 report |
|---|
| Radeon AI PRO R9700 | 8-bit | 128K | 106 tok/s | 0.4 s | PDF: Mellum2.1 12B A2.5B Thinking on Radeon AI PRO R9700 report |
|---|
| RTX 5090 | 8-bit | 128K | 263 tok/s | 0.1 s | PDF: Mellum2.1 12B A2.5B Thinking on RTX 5090 report |
|---|
| 2× RTX 3090 | 8-bit | 128K | 174 tok/s | 0.3 s | PDF: Mellum2.1 12B A2.5B Thinking on 2× RTX 3090 report |
|---|
| 2× RTX 4090 | 8-bit | 128K | 184 tok/s | 0.1 s | PDF: Mellum2.1 12B A2.5B Thinking on 2× RTX 4090 report |
|---|
| RTX PRO 5000 Blackwell 48 GB | 8-bit | 128K | 222 tok/s | 0.2 s | PDF: Mellum2.1 12B A2.5B Thinking on RTX PRO 5000 Blackwell 48 GB report |
|---|
| RTX 6000 Ada | 8-bit | 128K | 178 tok/s | 0.2 s | PDF: Mellum2.1 12B A2.5B Thinking on RTX 6000 Ada report |
|---|
| L40S | 8-bit | 128K | 165 tok/s | 0.3 s | PDF: Mellum2.1 12B A2.5B Thinking on L40S report |
|---|
| 2× RTX 5090 | 8-bit | 128K | 263 tok/s | 0.1 s | PDF: Mellum2.1 12B A2.5B Thinking on 2× RTX 5090 report |
|---|
| 4× RTX 3090 | 8-bit | 128K | 174 tok/s | 0.1 s | PDF: Mellum2.1 12B A2.5B Thinking on 4× RTX 3090 report |
|---|
| RTX PRO 6000 Blackwell | 8-bit | 128K | 263 tok/s | 0.1 s | PDF: Mellum2.1 12B A2.5B Thinking on RTX PRO 6000 Blackwell report |
|---|
| Mac mini M4 16 GB | 6-bit | 20K | 40 tok/s | 10.0 s | PDF: Mellum2.1 12B A2.5B Thinking on Mac mini M4 16 GB report |
|---|
| Mac mini M4 24 GB | 8-bit | 128K | 32 tok/s | 10.0 s | PDF: Mellum2.1 12B A2.5B Thinking on Mac mini M4 24 GB report |
|---|
| Mac mini M4 32 GB | 8-bit | 128K | 32 tok/s | 10.0 s | PDF: Mellum2.1 12B A2.5B Thinking on Mac mini M4 32 GB report |
|---|
| Mac mini M4 Pro 24 GB | 8-bit | 128K | 63 tok/s | 5.0 s | PDF: Mellum2.1 12B A2.5B Thinking on Mac mini M4 Pro 24 GB report |
|---|
| Mac mini M4 Pro 48 GB | 8-bit | 128K | 63 tok/s | 5.0 s | PDF: Mellum2.1 12B A2.5B Thinking on Mac mini M4 Pro 48 GB report |
|---|
| Mac mini M4 Pro 64 GB | 8-bit | 128K | 63 tok/s | 5.0 s | PDF: Mellum2.1 12B A2.5B Thinking on Mac mini M4 Pro 64 GB report |
|---|
| M4 Max 128 GB | 8-bit | 128K | 96 tok/s | 2.5 s | PDF: Mellum2.1 12B A2.5B Thinking on M4 Max 128 GB report |
|---|
| M5 Max 128 GB | 8-bit | 128K | 103 tok/s | 0.7 s | PDF: Mellum2.1 12B A2.5B Thinking on M5 Max 128 GB report |
|---|
| M3 Ultra 96 GB | 8-bit | 128K | 112 tok/s | 1.4 s | PDF: Mellum2.1 12B A2.5B Thinking on M3 Ultra 96 GB report |
|---|
| M3 Ultra 256 GB | 8-bit | 128K | 112 tok/s | 1.4 s | PDF: Mellum2.1 12B A2.5B Thinking on M3 Ultra 256 GB report |
|---|
| M3 Ultra 512 GB | 8-bit | 128K | 112 tok/s | 1.4 s | PDF: Mellum2.1 12B A2.5B Thinking on M3 Ultra 512 GB report |
|---|
| M5 Ultra 512 GB | 8-bit | 128K | 137 tok/s | 0.4 s | PDF: Mellum2.1 12B A2.5B Thinking on M5 Ultra 512 GB report |
|---|
| Ryzen AI Max+ 395 64 GB | 8-bit | 128K | 50 tok/s | 1.4 s | PDF: Mellum2.1 12B A2.5B Thinking on Ryzen AI Max+ 395 64 GB report |
|---|
| Ryzen AI Max+ 395 128 GB | 8-bit | 128K | 50 tok/s | 1.4 s | PDF: Mellum2.1 12B A2.5B Thinking on Ryzen AI Max+ 395 128 GB report |
|---|
| RTX Spark | 8-bit | 128K | 70 tok/s | 0.5 s | PDF: Mellum2.1 12B A2.5B Thinking on RTX Spark report |
|---|
| DGX Spark | 8-bit | 128K | 64 tok/s | 0.5 s | PDF: Mellum2.1 12B A2.5B Thinking on DGX Spark report |
|---|
| Dual DGX Spark | 8-bit | 128K | 64 tok/s | 0.3 s | PDF: Mellum2.1 12B A2.5B Thinking on Dual DGX Spark report |
|---|
| DGX Station GB300 | 8-bit | 128K | 452 tok/s | 0.1 s | PDF: Mellum2.1 12B A2.5B Thinking on DGX Station GB300 report |
|---|
| 2× RTX PRO 6000 Blackwell | 8-bit | 128K | 263 tok/s | 0.1 s | PDF: Mellum2.1 12B A2.5B Thinking on 2× RTX PRO 6000 Blackwell report |
|---|
| 4× RTX PRO 6000 Blackwell | 8-bit | 128K | 263 tok/s | 0.1 s | PDF: Mellum2.1 12B A2.5B Thinking on 4× RTX PRO 6000 Blackwell report |
|---|
| 8× RTX PRO 6000 Blackwell | 8-bit | 128K | 263 tok/s | 0.1 s | PDF: Mellum2.1 12B A2.5B Thinking on 8× RTX PRO 6000 Blackwell report |
|---|
| A100 80 GB SXM | 8-bit | 128K | 282 tok/s | 0.3 s | PDF: Mellum2.1 12B A2.5B Thinking on A100 80 GB SXM report |
|---|
| H100 SXM | 8-bit | 128K | 356 tok/s | 0.1 s | PDF: Mellum2.1 12B A2.5B Thinking on H100 SXM report |
|---|
| 4× H200 NVL | 8-bit | 128K | 405 tok/s | 0.1 s | PDF: Mellum2.1 12B A2.5B Thinking on 4× H200 NVL report |
|---|
| 8× H200 NVL | 8-bit | 128K | 405 tok/s | 0.1 s | PDF: Mellum2.1 12B A2.5B Thinking on 8× H200 NVL report |
|---|