| RTX 4060 | Too big | | | | PDF: gpt-oss 20B on RTX 4060 report |
|---|
| RTX 5060 | Too big | | | | PDF: gpt-oss 20B on RTX 5060 report |
|---|
| RTX 3070 | Too big | | | | PDF: gpt-oss 20B on RTX 3070 report |
|---|
| RTX 3080 10 GB | Too big | | | | PDF: gpt-oss 20B on RTX 3080 10 GB report |
|---|
| RTX 3060 12 GB | 3-bit | 40K | 119 tok/s | 1.4 s | PDF: gpt-oss 20B on RTX 3060 12 GB report |
|---|
| Arc B580 | 3-bit | 40K | 99 tok/s | 1.0 s | PDF: gpt-oss 20B on Arc B580 report |
|---|
| RTX 4070 | 3-bit | 40K | 156 tok/s | 0.6 s | PDF: gpt-oss 20B on RTX 4070 report |
|---|
| RTX 4070 Super | 3-bit | 40K | 156 tok/s | 0.5 s | PDF: gpt-oss 20B on RTX 4070 Super report |
|---|
| RTX 5070 | 3-bit | 40K | 193 tok/s | 0.6 s | PDF: gpt-oss 20B on RTX 5070 report |
|---|
| RTX 4060 Ti 16 GB | MXFP4 | 120K | 71 tok/s | 0.8 s | PDF: gpt-oss 20B on RTX 4060 Ti 16 GB report |
|---|
| RTX 5060 Ti 16 GB | MXFP4 | 120K | 104 tok/s | 0.8 s | PDF: gpt-oss 20B on RTX 5060 Ti 16 GB report |
|---|
| Arc A770 16 GB | MXFP4 | 120K | 86 tok/s | 0.9 s | PDF: gpt-oss 20B on Arc A770 16 GB report |
|---|
| Radeon RX 9070 XT | MXFP4 | 120K | 113 tok/s | 0.5 s | PDF: gpt-oss 20B on Radeon RX 9070 XT report |
|---|
| RTX 4070 Ti Super | MXFP4 | 120K | 145 tok/s | 0.4 s | PDF: gpt-oss 20B on RTX 4070 Ti Super report |
|---|
| RTX 4080 Super | MXFP4 | 120K | 156 tok/s | 0.3 s | PDF: gpt-oss 20B on RTX 4080 Super report |
|---|
| RTX 5070 Ti | MXFP4 | 120K | 181 tok/s | 0.4 s | PDF: gpt-oss 20B on RTX 5070 Ti report |
|---|
| RTX 5080 | MXFP4 | 120K | 190 tok/s | 0.3 s | PDF: gpt-oss 20B on RTX 5080 report |
|---|
| Radeon RX 7900 XTX | MXFP4 | 128K | 151 tok/s | 0.8 s | PDF: gpt-oss 20B on Radeon RX 7900 XTX report |
|---|
| RTX 3090 | MXFP4 | 128K | 187 tok/s | 0.5 s | PDF: gpt-oss 20B on RTX 3090 report |
|---|
| RTX 4090 | MXFP4 | 128K | 197 tok/s | 0.2 s | PDF: gpt-oss 20B on RTX 4090 report |
|---|
| Radeon AI PRO R9700 | MXFP4 | 128K | 113 tok/s | 0.5 s | PDF: gpt-oss 20B on Radeon AI PRO R9700 report |
|---|
| RTX 5090 | MXFP4 | 128K | 287 tok/s | 0.2 s | PDF: gpt-oss 20B on RTX 5090 report |
|---|
| 2× RTX 3090 | MXFP4 | 128K | 187 tok/s | 0.3 s | PDF: gpt-oss 20B on 2× RTX 3090 report |
|---|
| 2× RTX 4090 | MXFP4 | 128K | 197 tok/s | 0.1 s | PDF: gpt-oss 20B on 2× RTX 4090 report |
|---|
| RTX PRO 5000 Blackwell 48 GB | MXFP4 | 128K | 240 tok/s | 0.3 s | PDF: gpt-oss 20B on RTX PRO 5000 Blackwell 48 GB report |
|---|
| RTX 6000 Ada | MXFP4 | 128K | 190 tok/s | 0.2 s | PDF: gpt-oss 20B on RTX 6000 Ada report |
|---|
| L40S | MXFP4 | 128K | 176 tok/s | 0.3 s | PDF: gpt-oss 20B on L40S report |
|---|
| 2× RTX 5090 | MXFP4 | 128K | 287 tok/s | 0.1 s | PDF: gpt-oss 20B on 2× RTX 5090 report |
|---|
| 4× RTX 3090 | MXFP4 | 128K | 187 tok/s | 0.2 s | PDF: gpt-oss 20B on 4× RTX 3090 report |
|---|
| RTX PRO 6000 Blackwell | MXFP4 | 128K | 287 tok/s | 0.1 s | PDF: gpt-oss 20B on RTX PRO 6000 Blackwell report |
|---|
| Mac mini M4 16 GB | Too big | | | | PDF: gpt-oss 20B on Mac mini M4 16 GB report |
|---|
| Mac mini M4 24 GB | MXFP4 | 128K | 34 tok/s | 12 s | PDF: gpt-oss 20B on Mac mini M4 24 GB report |
|---|
| Mac mini M4 32 GB | MXFP4 | 128K | 34 tok/s | 12 s | PDF: gpt-oss 20B on Mac mini M4 32 GB report |
|---|
| Mac mini M4 Pro 24 GB | MXFP4 | 128K | 67 tok/s | 5.8 s | PDF: gpt-oss 20B on Mac mini M4 Pro 24 GB report |
|---|
| Mac mini M4 Pro 48 GB | MXFP4 | 128K | 67 tok/s | 5.8 s | PDF: gpt-oss 20B on Mac mini M4 Pro 48 GB report |
|---|
| Mac mini M4 Pro 64 GB | MXFP4 | 128K | 67 tok/s | 5.8 s | PDF: gpt-oss 20B on Mac mini M4 Pro 64 GB report |
|---|
| M4 Max 128 GB | MXFP4 | 128K | 104 tok/s | 2.9 s | PDF: gpt-oss 20B on M4 Max 128 GB report |
|---|
| M5 Max 128 GB | MXFP4 | 128K | 112 tok/s | 0.8 s | PDF: gpt-oss 20B on M5 Max 128 GB report |
|---|
| M3 Ultra 96 GB | MXFP4 | 128K | 122 tok/s | 1.6 s | PDF: gpt-oss 20B on M3 Ultra 96 GB report |
|---|
| M3 Ultra 256 GB | MXFP4 | 128K | 122 tok/s | 1.6 s | PDF: gpt-oss 20B on M3 Ultra 256 GB report |
|---|
| M3 Ultra 512 GB | MXFP4 | 128K | 122 tok/s | 1.6 s | PDF: gpt-oss 20B on M3 Ultra 512 GB report |
|---|
| M5 Ultra 512 GB | MXFP4 | 128K | 150 tok/s | 0.5 s | PDF: gpt-oss 20B on M5 Ultra 512 GB report |
|---|
| Ryzen AI Max+ 395 64 GB | MXFP4 | 128K | 53 tok/s | 1.7 s | PDF: gpt-oss 20B on Ryzen AI Max+ 395 64 GB report |
|---|
| Ryzen AI Max+ 395 128 GB | MXFP4 | 128K | 53 tok/s | 1.7 s | PDF: gpt-oss 20B on Ryzen AI Max+ 395 128 GB report |
|---|
| RTX Spark | MXFP4 | 128K | 73 tok/s | 0.6 s | PDF: gpt-oss 20B on RTX Spark report |
|---|
| DGX Spark | MXFP4 | 128K | 67 tok/s | 0.6 s | PDF: gpt-oss 20B on DGX Spark report |
|---|
| Dual DGX Spark | MXFP4 | 128K | 67 tok/s | 0.3 s | PDF: gpt-oss 20B on Dual DGX Spark report |
|---|
| DGX Station GB300 | MXFP4 | 128K | 511 tok/s | 0.1 s | PDF: gpt-oss 20B on DGX Station GB300 report |
|---|
| 2× RTX PRO 6000 Blackwell | MXFP4 | 128K | 287 tok/s | 0.1 s | PDF: gpt-oss 20B on 2× RTX PRO 6000 Blackwell report |
|---|
| 4× RTX PRO 6000 Blackwell | MXFP4 | 128K | 287 tok/s | 0.1 s | PDF: gpt-oss 20B on 4× RTX PRO 6000 Blackwell report |
|---|
| 8× RTX PRO 6000 Blackwell | MXFP4 | 128K | 287 tok/s | 0.1 s | PDF: gpt-oss 20B on 8× RTX PRO 6000 Blackwell report |
|---|
| A100 80 GB SXM | MXFP4 | 128K | 309 tok/s | 0.4 s | PDF: gpt-oss 20B on A100 80 GB SXM report |
|---|
| H100 SXM | MXFP4 | 128K | 395 tok/s | 0.1 s | PDF: gpt-oss 20B on H100 SXM report |
|---|
| 4× H200 NVL | MXFP4 | 128K | 454 tok/s | 0.1 s | PDF: gpt-oss 20B on 4× H200 NVL report |
|---|
| 8× H200 NVL | MXFP4 | 128K | 454 tok/s | 0.1 s | PDF: gpt-oss 20B on 8× H200 NVL report |
|---|