| RTX 4060 | 8-bit | 32K | 106 tok/s | 0.2 s | PDF: Qwen2.5 1.5B Instruct on RTX 4060 report |
|---|
| RTX 5060 | 8-bit | 32K | 165 tok/s | 0.2 s | PDF: Qwen2.5 1.5B Instruct on RTX 5060 report |
|---|
| RTX 3070 | 8-bit | 32K | 165 tok/s | 0.1 s | PDF: Qwen2.5 1.5B Instruct on RTX 3070 report |
|---|
| RTX 3080 10 GB | 8-bit | 32K | 255 tok/s | 0.1 s | PDF: Qwen2.5 1.5B Instruct on RTX 3080 10 GB report |
|---|
| RTX 3060 12 GB | 8-bit | 32K | 136 tok/s | 0.2 s | PDF: Qwen2.5 1.5B Instruct on RTX 3060 12 GB report |
|---|
| Arc B580 | 8-bit | 32K | 113 tok/s | 0.2 s | PDF: Qwen2.5 1.5B Instruct on Arc B580 report |
|---|
| RTX 4070 | 8-bit | 32K | 182 tok/s | 0.1 s | PDF: Qwen2.5 1.5B Instruct on RTX 4070 report |
|---|
| RTX 4070 Super | 8-bit | 32K | 182 tok/s | 0.1 s | PDF: Qwen2.5 1.5B Instruct on RTX 4070 Super report |
|---|
| RTX 5070 | 8-bit | 32K | 231 tok/s | 0.1 s | PDF: Qwen2.5 1.5B Instruct on RTX 5070 report |
|---|
| RTX 4060 Ti 16 GB | 8-bit | 32K | 111 tok/s | 0.1 s | PDF: Qwen2.5 1.5B Instruct on RTX 4060 Ti 16 GB report |
|---|
| RTX 5060 Ti 16 GB | 8-bit | 32K | 165 tok/s | 0.1 s | PDF: Qwen2.5 1.5B Instruct on RTX 5060 Ti 16 GB report |
|---|
| Arc A770 16 GB | 8-bit | 32K | 133 tok/s | 0.1 s | PDF: Qwen2.5 1.5B Instruct on Arc A770 16 GB report |
|---|
| Radeon RX 9070 XT | 8-bit | 32K | 176 tok/s | 0.1 s | PDF: Qwen2.5 1.5B Instruct on Radeon RX 9070 XT report |
|---|
| RTX 4070 Ti Super | 8-bit | 32K | 231 tok/s | 0.1 s | PDF: Qwen2.5 1.5B Instruct on RTX 4070 Ti Super report |
|---|
| RTX 4080 Super | 8-bit | 32K | 249 tok/s | 0.1 s | PDF: Qwen2.5 1.5B Instruct on RTX 4080 Super report |
|---|
| RTX 5070 Ti | 8-bit | 32K | 289 tok/s | 0.1 s | PDF: Qwen2.5 1.5B Instruct on RTX 5070 Ti report |
|---|
| RTX 5080 | 8-bit | 32K | 305 tok/s | 0.1 s | PDF: Qwen2.5 1.5B Instruct on RTX 5080 report |
|---|
| Radeon RX 7900 XTX | 8-bit | 32K | 235 tok/s | 0.1 s | PDF: Qwen2.5 1.5B Instruct on Radeon RX 7900 XTX report |
|---|
| RTX 3090 | 8-bit | 32K | 299 tok/s | 0.1 s | PDF: Qwen2.5 1.5B Instruct on RTX 3090 report |
|---|
| RTX 4090 | 8-bit | 32K | 316 tok/s | 0.1 s | PDF: Qwen2.5 1.5B Instruct on RTX 4090 report |
|---|
| Radeon AI PRO R9700 | 8-bit | 32K | 176 tok/s | 0.1 s | PDF: Qwen2.5 1.5B Instruct on Radeon AI PRO R9700 report |
|---|
| RTX 5090 | 8-bit | 32K | 466 tok/s | 0.1 s | PDF: Qwen2.5 1.5B Instruct on RTX 5090 report |
|---|
| 2× RTX 3090 | 8-bit | 32K | 299 tok/s | 0.1 s | PDF: Qwen2.5 1.5B Instruct on 2× RTX 3090 report |
|---|
| 2× RTX 4090 | 8-bit | 32K | 316 tok/s | 0.1 s | PDF: Qwen2.5 1.5B Instruct on 2× RTX 4090 report |
|---|
| RTX PRO 5000 Blackwell 48 GB | 8-bit | 32K | 387 tok/s | 0.1 s | PDF: Qwen2.5 1.5B Instruct on RTX PRO 5000 Blackwell 48 GB report |
|---|
| RTX 6000 Ada | 8-bit | 32K | 305 tok/s | 0.1 s | PDF: Qwen2.5 1.5B Instruct on RTX 6000 Ada report |
|---|
| L40S | 8-bit | 32K | 282 tok/s | 0.1 s | PDF: Qwen2.5 1.5B Instruct on L40S report |
|---|
| 2× RTX 5090 | 8-bit | 32K | 466 tok/s | 0.1 s | PDF: Qwen2.5 1.5B Instruct on 2× RTX 5090 report |
|---|
| 4× RTX 3090 | 8-bit | 32K | 299 tok/s | 0.1 s | PDF: Qwen2.5 1.5B Instruct on 4× RTX 3090 report |
|---|
| RTX PRO 6000 Blackwell | 8-bit | 32K | 466 tok/s | 0.1 s | PDF: Qwen2.5 1.5B Instruct on RTX PRO 6000 Blackwell report |
|---|
| Mac mini M4 16 GB | 8-bit | 32K | 53 tok/s | 1.9 s | PDF: Qwen2.5 1.5B Instruct on Mac mini M4 16 GB report |
|---|
| Mac mini M4 24 GB | 8-bit | 32K | 53 tok/s | 1.9 s | PDF: Qwen2.5 1.5B Instruct on Mac mini M4 24 GB report |
|---|
| Mac mini M4 32 GB | 8-bit | 32K | 53 tok/s | 1.9 s | PDF: Qwen2.5 1.5B Instruct on Mac mini M4 32 GB report |
|---|
| Mac mini M4 Pro 24 GB | 8-bit | 32K | 105 tok/s | 1.0 s | PDF: Qwen2.5 1.5B Instruct on Mac mini M4 Pro 24 GB report |
|---|
| Mac mini M4 Pro 48 GB | 8-bit | 32K | 105 tok/s | 1.0 s | PDF: Qwen2.5 1.5B Instruct on Mac mini M4 Pro 48 GB report |
|---|
| Mac mini M4 Pro 64 GB | 8-bit | 32K | 105 tok/s | 1.0 s | PDF: Qwen2.5 1.5B Instruct on Mac mini M4 Pro 64 GB report |
|---|
| M4 Max 128 GB | 8-bit | 32K | 160 tok/s | 0.5 s | PDF: Qwen2.5 1.5B Instruct on M4 Max 128 GB report |
|---|
| M5 Max 128 GB | 8-bit | 32K | 172 tok/s | 0.1 s | PDF: Qwen2.5 1.5B Instruct on M5 Max 128 GB report |
|---|
| M3 Ultra 96 GB | 8-bit | 32K | 188 tok/s | 0.3 s | PDF: Qwen2.5 1.5B Instruct on M3 Ultra 96 GB report |
|---|
| M3 Ultra 256 GB | 8-bit | 32K | 188 tok/s | 0.3 s | PDF: Qwen2.5 1.5B Instruct on M3 Ultra 256 GB report |
|---|
| M3 Ultra 512 GB | 8-bit | 32K | 188 tok/s | 0.3 s | PDF: Qwen2.5 1.5B Instruct on M3 Ultra 512 GB report |
|---|
| M5 Ultra 512 GB | 8-bit | 32K | 230 tok/s | 0.1 s | PDF: Qwen2.5 1.5B Instruct on M5 Ultra 512 GB report |
|---|
| Ryzen AI Max+ 395 64 GB | 8-bit | 32K | 83 tok/s | 0.3 s | PDF: Qwen2.5 1.5B Instruct on Ryzen AI Max+ 395 64 GB report |
|---|
| Ryzen AI Max+ 395 128 GB | 8-bit | 32K | 83 tok/s | 0.3 s | PDF: Qwen2.5 1.5B Instruct on Ryzen AI Max+ 395 128 GB report |
|---|
| RTX Spark | 8-bit | 32K | 116 tok/s | 0.1 s | PDF: Qwen2.5 1.5B Instruct on RTX Spark report |
|---|
| DGX Spark | 8-bit | 32K | 106 tok/s | 0.1 s | PDF: Qwen2.5 1.5B Instruct on DGX Spark report |
|---|
| Dual DGX Spark | 8-bit | 32K | 106 tok/s | 0.1 s | PDF: Qwen2.5 1.5B Instruct on Dual DGX Spark report |
|---|
| DGX Station GB300 | 8-bit | 32K | 855 tok/s | 0.1 s | PDF: Qwen2.5 1.5B Instruct on DGX Station GB300 report |
|---|
| 2× RTX PRO 6000 Blackwell | 8-bit | 32K | 466 tok/s | 0.1 s | PDF: Qwen2.5 1.5B Instruct on 2× RTX PRO 6000 Blackwell report |
|---|
| 4× RTX PRO 6000 Blackwell | 8-bit | 32K | 466 tok/s | 0.1 s | PDF: Qwen2.5 1.5B Instruct on 4× RTX PRO 6000 Blackwell report |
|---|
| 8× RTX PRO 6000 Blackwell | 8-bit | 32K | 466 tok/s | 0.1 s | PDF: Qwen2.5 1.5B Instruct on 8× RTX PRO 6000 Blackwell report |
|---|
| A100 80 GB SXM | 8-bit | 32K | 503 tok/s | 0.1 s | PDF: Qwen2.5 1.5B Instruct on A100 80 GB SXM report |
|---|
| H100 SXM | 8-bit | 32K | 650 tok/s | 0.1 s | PDF: Qwen2.5 1.5B Instruct on H100 SXM report |
|---|
| 4× H200 NVL | 8-bit | 32K | 753 tok/s | 0.1 s | PDF: Qwen2.5 1.5B Instruct on 4× H200 NVL report |
|---|
| 8× H200 NVL | 8-bit | 32K | 753 tok/s | 0.1 s | PDF: Qwen2.5 1.5B Instruct on 8× H200 NVL report |
|---|