| RTX 4060 | 8-bit | 2K | 100 tok/s | 0.2 s | PDF: Gpt2 XL on RTX 4060 report |
|---|
| RTX 5060 | 8-bit | 2K | 151 tok/s | 0.2 s | PDF: Gpt2 XL on RTX 5060 report |
|---|
| RTX 3070 | 8-bit | 2K | 151 tok/s | 0.2 s | PDF: Gpt2 XL on RTX 3070 report |
|---|
| RTX 3080 10 GB | 8-bit | 2K | 223 tok/s | 0.1 s | PDF: Gpt2 XL on RTX 3080 10 GB report |
|---|
| RTX 3060 12 GB | 8-bit | 2K | 127 tok/s | 0.3 s | PDF: Gpt2 XL on RTX 3060 12 GB report |
|---|
| Arc B580 | 8-bit | 2K | 100 tok/s | 0.2 s | PDF: Gpt2 XL on Arc B580 report |
|---|
| RTX 4070 | 8-bit | 2K | 166 tok/s | 0.1 s | PDF: Gpt2 XL on RTX 4070 report |
|---|
| RTX 4070 Super | 8-bit | 2K | 166 tok/s | 0.1 s | PDF: Gpt2 XL on RTX 4070 Super report |
|---|
| RTX 5070 | 8-bit | 2K | 204 tok/s | 0.1 s | PDF: Gpt2 XL on RTX 5070 report |
|---|
| RTX 4060 Ti 16 GB | 8-bit | 2K | 105 tok/s | 0.2 s | PDF: Gpt2 XL on RTX 4060 Ti 16 GB report |
|---|
| RTX 5060 Ti 16 GB | 8-bit | 2K | 151 tok/s | 0.1 s | PDF: Gpt2 XL on RTX 5060 Ti 16 GB report |
|---|
| Arc A770 16 GB | 8-bit | 2K | 115 tok/s | 0.2 s | PDF: Gpt2 XL on Arc A770 16 GB report |
|---|
| Radeon RX 9070 XT | 8-bit | 2K | 151 tok/s | 0.1 s | PDF: Gpt2 XL on Radeon RX 9070 XT report |
|---|
| RTX 4070 Ti Super | 8-bit | 2K | 204 tok/s | 0.1 s | PDF: Gpt2 XL on RTX 4070 Ti Super report |
|---|
| RTX 4080 Super | 8-bit | 2K | 218 tok/s | 0.1 s | PDF: Gpt2 XL on RTX 4080 Super report |
|---|
| RTX 5070 Ti | 8-bit | 2K | 248 tok/s | 0.1 s | PDF: Gpt2 XL on RTX 5070 Ti report |
|---|
| RTX 5080 | 8-bit | 2K | 259 tok/s | 0.1 s | PDF: Gpt2 XL on RTX 5080 report |
|---|
| Radeon RX 7900 XTX | 8-bit | 2K | 192 tok/s | 0.2 s | PDF: Gpt2 XL on Radeon RX 7900 XTX report |
|---|
| RTX 3090 | 8-bit | 2K | 255 tok/s | 0.1 s | PDF: Gpt2 XL on RTX 3090 report |
|---|
| RTX 4090 | 8-bit | 2K | 267 tok/s | 0.1 s | PDF: Gpt2 XL on RTX 4090 report |
|---|
| Radeon AI PRO R9700 | 8-bit | 2K | 151 tok/s | 0.1 s | PDF: Gpt2 XL on Radeon AI PRO R9700 report |
|---|
| RTX 5090 | 8-bit | 2K | 366 tok/s | 0.1 s | PDF: Gpt2 XL on RTX 5090 report |
|---|
| 2× RTX 3090 | 8-bit | 2K | 255 tok/s | 0.1 s | PDF: Gpt2 XL on 2× RTX 3090 report |
|---|
| 2× RTX 4090 | 8-bit | 2K | 267 tok/s | 0.1 s | PDF: Gpt2 XL on 2× RTX 4090 report |
|---|
| RTX PRO 5000 Blackwell 48 GB | 8-bit | 2K | 316 tok/s | 0.1 s | PDF: Gpt2 XL on RTX PRO 5000 Blackwell 48 GB report |
|---|
| RTX 6000 Ada | 8-bit | 2K | 259 tok/s | 0.1 s | PDF: Gpt2 XL on RTX 6000 Ada report |
|---|
| L40S | 8-bit | 2K | 243 tok/s | 0.1 s | PDF: Gpt2 XL on L40S report |
|---|
| 2× RTX 5090 | 8-bit | 2K | 366 tok/s | 0.1 s | PDF: Gpt2 XL on 2× RTX 5090 report |
|---|
| 4× RTX 3090 | 8-bit | 2K | 255 tok/s | 0.1 s | PDF: Gpt2 XL on 4× RTX 3090 report |
|---|
| RTX PRO 6000 Blackwell | 8-bit | 2K | 366 tok/s | 0.1 s | PDF: Gpt2 XL on RTX PRO 6000 Blackwell report |
|---|
| Mac mini M4 16 GB | 8-bit | 2K | 49 tok/s | 2.2 s | PDF: Gpt2 XL on Mac mini M4 16 GB report |
|---|
| Mac mini M4 24 GB | 8-bit | 2K | 49 tok/s | 2.2 s | PDF: Gpt2 XL on Mac mini M4 24 GB report |
|---|
| Mac mini M4 32 GB | 8-bit | 2K | 49 tok/s | 2.2 s | PDF: Gpt2 XL on Mac mini M4 32 GB report |
|---|
| Mac mini M4 Pro 24 GB | 8-bit | 2K | 90 tok/s | 1.1 s | PDF: Gpt2 XL on Mac mini M4 Pro 24 GB report |
|---|
| Mac mini M4 Pro 48 GB | 8-bit | 2K | 90 tok/s | 1.1 s | PDF: Gpt2 XL on Mac mini M4 Pro 48 GB report |
|---|
| Mac mini M4 Pro 64 GB | 8-bit | 2K | 90 tok/s | 1.1 s | PDF: Gpt2 XL on Mac mini M4 Pro 64 GB report |
|---|
| M4 Max 128 GB | 8-bit | 2K | 128 tok/s | 0.5 s | PDF: Gpt2 XL on M4 Max 128 GB report |
|---|
| M5 Max 128 GB | 8-bit | 2K | 136 tok/s | 0.2 s | PDF: Gpt2 XL on M5 Max 128 GB report |
|---|
| M3 Ultra 96 GB | 8-bit | 2K | 145 tok/s | 0.3 s | PDF: Gpt2 XL on M3 Ultra 96 GB report |
|---|
| M3 Ultra 256 GB | 8-bit | 2K | 145 tok/s | 0.3 s | PDF: Gpt2 XL on M3 Ultra 256 GB report |
|---|
| M3 Ultra 512 GB | 8-bit | 2K | 145 tok/s | 0.3 s | PDF: Gpt2 XL on M3 Ultra 512 GB report |
|---|
| M5 Ultra 512 GB | 8-bit | 2K | 169 tok/s | 0.1 s | PDF: Gpt2 XL on M5 Ultra 512 GB report |
|---|
| Ryzen AI Max+ 395 64 GB | 8-bit | 2K | 77 tok/s | 0.3 s | PDF: Gpt2 XL on Ryzen AI Max+ 395 64 GB report |
|---|
| Ryzen AI Max+ 395 128 GB | 8-bit | 2K | 77 tok/s | 0.3 s | PDF: Gpt2 XL on Ryzen AI Max+ 395 128 GB report |
|---|
| RTX Spark | 8-bit | 2K | 109 tok/s | 0.1 s | PDF: Gpt2 XL on RTX Spark report |
|---|
| DGX Spark | 8-bit | 2K | 101 tok/s | 0.1 s | PDF: Gpt2 XL on DGX Spark report |
|---|
| Dual DGX Spark | 8-bit | 2K | 101 tok/s | 0.1 s | PDF: Gpt2 XL on Dual DGX Spark report |
|---|
| DGX Station GB300 | 8-bit | 2K | 566 tok/s | 0.1 s | PDF: Gpt2 XL on DGX Station GB300 report |
|---|
| 2× RTX PRO 6000 Blackwell | 8-bit | 2K | 366 tok/s | 0.1 s | PDF: Gpt2 XL on 2× RTX PRO 6000 Blackwell report |
|---|
| 4× RTX PRO 6000 Blackwell | 8-bit | 2K | 366 tok/s | 0.1 s | PDF: Gpt2 XL on 4× RTX PRO 6000 Blackwell report |
|---|
| 8× RTX PRO 6000 Blackwell | 8-bit | 2K | 366 tok/s | 0.1 s | PDF: Gpt2 XL on 8× RTX PRO 6000 Blackwell report |
|---|
| A100 80 GB SXM | 8-bit | 2K | 388 tok/s | 0.1 s | PDF: Gpt2 XL on A100 80 GB SXM report |
|---|
| H100 SXM | 8-bit | 2K | 469 tok/s | 0.1 s | PDF: Gpt2 XL on H100 SXM report |
|---|
| 4× H200 NVL | 8-bit | 2K | 520 tok/s | 0.1 s | PDF: Gpt2 XL on 4× H200 NVL report |
|---|
| 8× H200 NVL | 8-bit | 2K | 520 tok/s | 0.1 s | PDF: Gpt2 XL on 8× H200 NVL report |
|---|