| RTX 4060 | Too big | | | | PDF: Qwen1.5 7B on RTX 4060 report |
|---|
| RTX 5060 | Too big | | | | PDF: Qwen1.5 7B on RTX 5060 report |
|---|
| RTX 3070 | Too big | | | | PDF: Qwen1.5 7B on RTX 3070 report |
|---|
| RTX 3080 10 GB | Too big | | | | PDF: Qwen1.5 7B on RTX 3080 10 GB report |
|---|
| RTX 3060 12 GB | Too big | | | | PDF: Qwen1.5 7B on RTX 3060 12 GB report |
|---|
| Arc B580 | Too big | | | | PDF: Qwen1.5 7B on Arc B580 report |
|---|
| RTX 4070 | Too big | | | | PDF: Qwen1.5 7B on RTX 4070 report |
|---|
| RTX 4070 Super | Too big | | | | PDF: Qwen1.5 7B on RTX 4070 Super report |
|---|
| RTX 5070 | Too big | | | | PDF: Qwen1.5 7B on RTX 5070 report |
|---|
| RTX 4060 Ti 16 GB | 6-bit | 16K | 34 tok/s | 0.7 s | PDF: Qwen1.5 7B on RTX 4060 Ti 16 GB report |
|---|
| RTX 5060 Ti 16 GB | 6-bit | 16K | 51 tok/s | 0.6 s | PDF: Qwen1.5 7B on RTX 5060 Ti 16 GB report |
|---|
| Arc A770 16 GB | 6-bit | 16K | 44 tok/s | 0.7 s | PDF: Qwen1.5 7B on Arc A770 16 GB report |
|---|
| Radeon RX 9070 XT | 6-bit | 16K | 60 tok/s | 0.4 s | PDF: Qwen1.5 7B on Radeon RX 9070 XT report |
|---|
| RTX 4070 Ti Super | 6-bit | 16K | 75 tok/s | 0.3 s | PDF: Qwen1.5 7B on RTX 4070 Ti Super report |
|---|
| RTX 4080 Super | 6-bit | 16K | 82 tok/s | 0.3 s | PDF: Qwen1.5 7B on RTX 4080 Super report |
|---|
| RTX 5070 Ti | 6-bit | 16K | 98 tok/s | 0.3 s | PDF: Qwen1.5 7B on RTX 5070 Ti report |
|---|
| RTX 5080 | 6-bit | 16K | 104 tok/s | 0.3 s | PDF: Qwen1.5 7B on RTX 5080 report |
|---|
| Radeon RX 7900 XTX | 8-bit | 28K | 68 tok/s | 0.6 s | PDF: Qwen1.5 7B on Radeon RX 7900 XTX report |
|---|
| RTX 3090 | 8-bit | 28K | 80 tok/s | 0.4 s | PDF: Qwen1.5 7B on RTX 3090 report |
|---|
| RTX 4090 | 8-bit | 28K | 86 tok/s | 0.2 s | PDF: Qwen1.5 7B on RTX 4090 report |
|---|
| Radeon AI PRO R9700 | 8-bit | 32K | 47 tok/s | 0.4 s | PDF: Qwen1.5 7B on Radeon AI PRO R9700 report |
|---|
| RTX 5090 | 8-bit | 32K | 143 tok/s | 0.1 s | PDF: Qwen1.5 7B on RTX 5090 report |
|---|
| 2× RTX 3090 | 8-bit | 32K | 80 tok/s | 0.2 s | PDF: Qwen1.5 7B on 2× RTX 3090 report |
|---|
| 2× RTX 4090 | 8-bit | 32K | 86 tok/s | 0.1 s | PDF: Qwen1.5 7B on 2× RTX 4090 report |
|---|
| RTX PRO 5000 Blackwell 48 GB | 8-bit | 32K | 111 tok/s | 0.2 s | PDF: Qwen1.5 7B on RTX PRO 5000 Blackwell 48 GB report |
|---|
| RTX 6000 Ada | 8-bit | 32K | 82 tok/s | 0.2 s | PDF: Qwen1.5 7B on RTX 6000 Ada report |
|---|
| L40S | 8-bit | 32K | 74 tok/s | 0.3 s | PDF: Qwen1.5 7B on L40S report |
|---|
| 2× RTX 5090 | 8-bit | 32K | 143 tok/s | 0.1 s | PDF: Qwen1.5 7B on 2× RTX 5090 report |
|---|
| 4× RTX 3090 | 8-bit | 32K | 80 tok/s | 0.1 s | PDF: Qwen1.5 7B on 4× RTX 3090 report |
|---|
| RTX PRO 6000 Blackwell | 8-bit | 32K | 143 tok/s | 0.1 s | PDF: Qwen1.5 7B on RTX PRO 6000 Blackwell report |
|---|
| Mac mini M4 16 GB | Too big | | | | PDF: Qwen1.5 7B on Mac mini M4 16 GB report |
|---|
| Mac mini M4 24 GB | 6-bit | 16K | 16 tok/s | 9.2 s | PDF: Qwen1.5 7B on Mac mini M4 24 GB report |
|---|
| Mac mini M4 32 GB | 8-bit | 20K | 13 tok/s | 9.2 s | PDF: Qwen1.5 7B on Mac mini M4 32 GB report |
|---|
| Mac mini M4 Pro 24 GB | 6-bit | 16K | 35 tok/s | 4.6 s | PDF: Qwen1.5 7B on Mac mini M4 Pro 24 GB report |
|---|
| Mac mini M4 Pro 48 GB | 8-bit | 32K | 28 tok/s | 4.6 s | PDF: Qwen1.5 7B on Mac mini M4 Pro 48 GB report |
|---|
| Mac mini M4 Pro 64 GB | 8-bit | 32K | 28 tok/s | 4.6 s | PDF: Qwen1.5 7B on Mac mini M4 Pro 64 GB report |
|---|
| M4 Max 128 GB | 8-bit | 32K | 48 tok/s | 2.3 s | PDF: Qwen1.5 7B on M4 Max 128 GB report |
|---|
| M5 Max 128 GB | 8-bit | 32K | 53 tok/s | 0.7 s | PDF: Qwen1.5 7B on M5 Max 128 GB report |
|---|
| M3 Ultra 96 GB | 8-bit | 32K | 60 tok/s | 1.3 s | PDF: Qwen1.5 7B on M3 Ultra 96 GB report |
|---|
| M3 Ultra 256 GB | 8-bit | 32K | 60 tok/s | 1.3 s | PDF: Qwen1.5 7B on M3 Ultra 256 GB report |
|---|
| M3 Ultra 512 GB | 8-bit | 32K | 60 tok/s | 1.3 s | PDF: Qwen1.5 7B on M3 Ultra 512 GB report |
|---|
| M5 Ultra 512 GB | 8-bit | 32K | 82 tok/s | 0.4 s | PDF: Qwen1.5 7B on M5 Ultra 512 GB report |
|---|
| Ryzen AI Max+ 395 64 GB | 8-bit | 32K | 20 tok/s | 1.3 s | PDF: Qwen1.5 7B on Ryzen AI Max+ 395 64 GB report |
|---|
| Ryzen AI Max+ 395 128 GB | 8-bit | 32K | 20 tok/s | 1.3 s | PDF: Qwen1.5 7B on Ryzen AI Max+ 395 128 GB report |
|---|
| RTX Spark | 8-bit | 32K | 27 tok/s | 0.5 s | PDF: Qwen1.5 7B on RTX Spark report |
|---|
| DGX Spark | 8-bit | 32K | 25 tok/s | 0.5 s | PDF: Qwen1.5 7B on DGX Spark report |
|---|
| Dual DGX Spark | 8-bit | 32K | 25 tok/s | 0.3 s | PDF: Qwen1.5 7B on Dual DGX Spark report |
|---|
| DGX Station GB300 | 8-bit | 32K | 404 tok/s | 0.1 s | PDF: Qwen1.5 7B on DGX Station GB300 report |
|---|
| 2× RTX PRO 6000 Blackwell | 8-bit | 32K | 143 tok/s | 0.1 s | PDF: Qwen1.5 7B on 2× RTX PRO 6000 Blackwell report |
|---|
| 4× RTX PRO 6000 Blackwell | 8-bit | 32K | 143 tok/s | 0.1 s | PDF: Qwen1.5 7B on 4× RTX PRO 6000 Blackwell report |
|---|
| 8× RTX PRO 6000 Blackwell | 8-bit | 32K | 143 tok/s | 0.1 s | PDF: Qwen1.5 7B on 8× RTX PRO 6000 Blackwell report |
|---|
| A100 80 GB SXM | 8-bit | 32K | 160 tok/s | 0.3 s | PDF: Qwen1.5 7B on A100 80 GB SXM report |
|---|
| H100 SXM | 8-bit | 32K | 239 tok/s | 0.1 s | PDF: Qwen1.5 7B on H100 SXM report |
|---|
| 4× H200 NVL | 8-bit | 32K | 312 tok/s | 0.1 s | PDF: Qwen1.5 7B on 4× H200 NVL report |
|---|
| 8× H200 NVL | 8-bit | 32K | 312 tok/s | 0.1 s | PDF: Qwen1.5 7B on 8× H200 NVL report |
|---|