| RTX 4060 | 8-bit | 40K | 199 tok/s | 0.1 s | PDF: Qwen3 0.6B on RTX 4060 report |
|---|
| RTX 5060 | 8-bit | 40K | 295 tok/s | 0.1 s | PDF: Qwen3 0.6B on RTX 5060 report |
|---|
| RTX 3070 | 8-bit | 40K | 295 tok/s | 0.1 s | PDF: Qwen3 0.6B on RTX 3070 report |
|---|
| RTX 3080 10 GB | 8-bit | 40K | 427 tok/s | 0.1 s | PDF: Qwen3 0.6B on RTX 3080 10 GB report |
|---|
| RTX 3060 12 GB | 8-bit | 40K | 249 tok/s | 0.1 s | PDF: Qwen3 0.6B on RTX 3060 12 GB report |
|---|
| Arc B580 | 8-bit | 40K | 193 tok/s | 0.1 s | PDF: Qwen3 0.6B on Arc B580 report |
|---|
| RTX 4070 | 8-bit | 40K | 322 tok/s | 0.1 s | PDF: Qwen3 0.6B on RTX 4070 report |
|---|
| RTX 4070 Super | 8-bit | 40K | 322 tok/s | 0.1 s | PDF: Qwen3 0.6B on RTX 4070 Super report |
|---|
| RTX 5070 | 8-bit | 40K | 394 tok/s | 0.1 s | PDF: Qwen3 0.6B on RTX 5070 report |
|---|
| RTX 4060 Ti 16 GB | 8-bit | 40K | 208 tok/s | 0.1 s | PDF: Qwen3 0.6B on RTX 4060 Ti 16 GB report |
|---|
| RTX 5060 Ti 16 GB | 8-bit | 40K | 295 tok/s | 0.1 s | PDF: Qwen3 0.6B on RTX 5060 Ti 16 GB report |
|---|
| Arc A770 16 GB | 8-bit | 40K | 221 tok/s | 0.1 s | PDF: Qwen3 0.6B on Arc A770 16 GB report |
|---|
| Radeon RX 9070 XT | 8-bit | 40K | 287 tok/s | 0.1 s | PDF: Qwen3 0.6B on Radeon RX 9070 XT report |
|---|
| RTX 4070 Ti Super | 8-bit | 40K | 394 tok/s | 0.1 s | PDF: Qwen3 0.6B on RTX 4070 Ti Super report |
|---|
| RTX 4080 Super | 8-bit | 40K | 418 tok/s | 0.1 s | PDF: Qwen3 0.6B on RTX 4080 Super report |
|---|
| RTX 5070 Ti | 8-bit | 40K | 473 tok/s | 0.1 s | PDF: Qwen3 0.6B on RTX 5070 Ti report |
|---|
| RTX 5080 | 8-bit | 40K | 493 tok/s | 0.1 s | PDF: Qwen3 0.6B on RTX 5080 report |
|---|
| Radeon RX 7900 XTX | 8-bit | 40K | 359 tok/s | 0.1 s | PDF: Qwen3 0.6B on Radeon RX 7900 XTX report |
|---|
| RTX 3090 | 8-bit | 40K | 486 tok/s | 0.1 s | PDF: Qwen3 0.6B on RTX 3090 report |
|---|
| RTX 4090 | 8-bit | 40K | 507 tok/s | 0.1 s | PDF: Qwen3 0.6B on RTX 4090 report |
|---|
| Radeon AI PRO R9700 | 8-bit | 40K | 287 tok/s | 0.1 s | PDF: Qwen3 0.6B on Radeon AI PRO R9700 report |
|---|
| RTX 5090 | 8-bit | 40K | 677 tok/s | 0.1 s | PDF: Qwen3 0.6B on RTX 5090 report |
|---|
| 2× RTX 3090 | 8-bit | 40K | 486 tok/s | 0.1 s | PDF: Qwen3 0.6B on 2× RTX 3090 report |
|---|
| 2× RTX 4090 | 8-bit | 40K | 507 tok/s | 0.1 s | PDF: Qwen3 0.6B on 2× RTX 4090 report |
|---|
| RTX PRO 5000 Blackwell 48 GB | 8-bit | 40K | 592 tok/s | 0.1 s | PDF: Qwen3 0.6B on RTX PRO 5000 Blackwell 48 GB report |
|---|
| RTX 6000 Ada | 8-bit | 40K | 493 tok/s | 0.1 s | PDF: Qwen3 0.6B on RTX 6000 Ada report |
|---|
| L40S | 8-bit | 40K | 463 tok/s | 0.1 s | PDF: Qwen3 0.6B on L40S report |
|---|
| 2× RTX 5090 | 8-bit | 40K | 677 tok/s | 0.1 s | PDF: Qwen3 0.6B on 2× RTX 5090 report |
|---|
| 4× RTX 3090 | 8-bit | 40K | 486 tok/s | 0.1 s | PDF: Qwen3 0.6B on 4× RTX 3090 report |
|---|
| RTX PRO 6000 Blackwell | 8-bit | 40K | 677 tok/s | 0.1 s | PDF: Qwen3 0.6B on RTX PRO 6000 Blackwell report |
|---|
| Mac mini M4 16 GB | 8-bit | 40K | 97 tok/s | 0.9 s | PDF: Qwen3 0.6B on Mac mini M4 16 GB report |
|---|
| Mac mini M4 24 GB | 8-bit | 40K | 97 tok/s | 0.9 s | PDF: Qwen3 0.6B on Mac mini M4 24 GB report |
|---|
| Mac mini M4 32 GB | 8-bit | 40K | 97 tok/s | 0.9 s | PDF: Qwen3 0.6B on Mac mini M4 32 GB report |
|---|
| Mac mini M4 Pro 24 GB | 8-bit | 40K | 172 tok/s | 0.4 s | PDF: Qwen3 0.6B on Mac mini M4 Pro 24 GB report |
|---|
| Mac mini M4 Pro 48 GB | 8-bit | 40K | 172 tok/s | 0.4 s | PDF: Qwen3 0.6B on Mac mini M4 Pro 48 GB report |
|---|
| Mac mini M4 Pro 64 GB | 8-bit | 40K | 172 tok/s | 0.4 s | PDF: Qwen3 0.6B on Mac mini M4 Pro 64 GB report |
|---|
| M4 Max 128 GB | 8-bit | 40K | 239 tok/s | 0.2 s | PDF: Qwen3 0.6B on M4 Max 128 GB report |
|---|
| M5 Max 128 GB | 8-bit | 40K | 252 tok/s | 0.1 s | PDF: Qwen3 0.6B on M5 Max 128 GB report |
|---|
| M3 Ultra 96 GB | 8-bit | 40K | 267 tok/s | 0.1 s | PDF: Qwen3 0.6B on M3 Ultra 96 GB report |
|---|
| M3 Ultra 256 GB | 8-bit | 40K | 267 tok/s | 0.1 s | PDF: Qwen3 0.6B on M3 Ultra 256 GB report |
|---|
| M3 Ultra 512 GB | 8-bit | 40K | 267 tok/s | 0.1 s | PDF: Qwen3 0.6B on M3 Ultra 512 GB report |
|---|
| M5 Ultra 512 GB | 8-bit | 40K | 306 tok/s | 0.1 s | PDF: Qwen3 0.6B on M5 Ultra 512 GB report |
|---|
| Ryzen AI Max+ 395 64 GB | 8-bit | 40K | 152 tok/s | 0.1 s | PDF: Qwen3 0.6B on Ryzen AI Max+ 395 64 GB report |
|---|
| Ryzen AI Max+ 395 128 GB | 8-bit | 40K | 152 tok/s | 0.1 s | PDF: Qwen3 0.6B on Ryzen AI Max+ 395 128 GB report |
|---|
| RTX Spark | 8-bit | 40K | 215 tok/s | 0.1 s | PDF: Qwen3 0.6B on RTX Spark report |
|---|
| DGX Spark | 8-bit | 40K | 199 tok/s | 0.1 s | PDF: Qwen3 0.6B on DGX Spark report |
|---|
| Dual DGX Spark | 8-bit | 40K | 199 tok/s | 0.1 s | PDF: Qwen3 0.6B on Dual DGX Spark report |
|---|
| DGX Station GB300 | 8-bit | 40K | 999 tok/s | 0.1 s | PDF: Qwen3 0.6B on DGX Station GB300 report |
|---|
| 2× RTX PRO 6000 Blackwell | 8-bit | 40K | 677 tok/s | 0.1 s | PDF: Qwen3 0.6B on 2× RTX PRO 6000 Blackwell report |
|---|
| 4× RTX PRO 6000 Blackwell | 8-bit | 40K | 677 tok/s | 0.1 s | PDF: Qwen3 0.6B on 4× RTX PRO 6000 Blackwell report |
|---|
| 8× RTX PRO 6000 Blackwell | 8-bit | 40K | 677 tok/s | 0.1 s | PDF: Qwen3 0.6B on 8× RTX PRO 6000 Blackwell report |
|---|
| A100 80 GB SXM | 8-bit | 40K | 715 tok/s | 0.1 s | PDF: Qwen3 0.6B on A100 80 GB SXM report |
|---|
| H100 SXM | 8-bit | 40K | 847 tok/s | 0.1 s | PDF: Qwen3 0.6B on H100 SXM report |
|---|
| 4× H200 NVL | 8-bit | 40K | 928 tok/s | 0.1 s | PDF: Qwen3 0.6B on 4× H200 NVL report |
|---|
| 8× H200 NVL | 8-bit | 40K | 928 tok/s | 0.1 s | PDF: Qwen3 0.6B on 8× H200 NVL report |
|---|