| RTX 4060 | Too big | | | | PDF: LLaDA2.1 Mini on RTX 4060 report |
|---|
| RTX 5060 | Too big | | | | PDF: LLaDA2.1 Mini on RTX 5060 report |
|---|
| RTX 3070 | Too big | | | | PDF: LLaDA2.1 Mini on RTX 3070 report |
|---|
| RTX 3080 10 GB | 3-bit | 32K | 397 tok/s | 0.2 s | PDF: LLaDA2.1 Mini on RTX 3080 10 GB report |
|---|
| RTX 3060 12 GB | 4-bit | 32K | 215 tok/s | 0.5 s | PDF: LLaDA2.1 Mini on RTX 3060 12 GB report |
|---|
| Arc B580 | 4-bit | 32K | 172 tok/s | 0.3 s | PDF: LLaDA2.1 Mini on Arc B580 report |
|---|
| RTX 4070 | 4-bit | 32K | 273 tok/s | 0.2 s | PDF: LLaDA2.1 Mini on RTX 4070 report |
|---|
| RTX 4070 Super | 4-bit | 32K | 273 tok/s | 0.2 s | PDF: LLaDA2.1 Mini on RTX 4070 Super report |
|---|
| RTX 5070 | 4-bit | 32K | 328 tok/s | 0.2 s | PDF: LLaDA2.1 Mini on RTX 5070 report |
|---|
| RTX 4060 Ti 16 GB | 6-bit | 32K | 142 tok/s | 0.3 s | PDF: LLaDA2.1 Mini on RTX 4060 Ti 16 GB report |
|---|
| RTX 5060 Ti 16 GB | 6-bit | 32K | 202 tok/s | 0.3 s | PDF: LLaDA2.1 Mini on RTX 5060 Ti 16 GB report |
|---|
| Arc A770 16 GB | 6-bit | 32K | 161 tok/s | 0.3 s | PDF: LLaDA2.1 Mini on Arc A770 16 GB report |
|---|
| Radeon RX 9070 XT | 6-bit | 32K | 206 tok/s | 0.2 s | PDF: LLaDA2.1 Mini on Radeon RX 9070 XT report |
|---|
| RTX 4070 Ti Super | 6-bit | 32K | 270 tok/s | 0.1 s | PDF: LLaDA2.1 Mini on RTX 4070 Ti Super report |
|---|
| RTX 4080 Super | 6-bit | 32K | 287 tok/s | 0.1 s | PDF: LLaDA2.1 Mini on RTX 4080 Super report |
|---|
| RTX 5070 Ti | 6-bit | 32K | 325 tok/s | 0.1 s | PDF: LLaDA2.1 Mini on RTX 5070 Ti report |
|---|
| RTX 5080 | 6-bit | 32K | 339 tok/s | 0.1 s | PDF: LLaDA2.1 Mini on RTX 5080 report |
|---|
| Radeon RX 7900 XTX | 8-bit | 32K | 225 tok/s | 0.3 s | PDF: LLaDA2.1 Mini on Radeon RX 7900 XTX report |
|---|
| RTX 3090 | 8-bit | 32K | 284 tok/s | 0.2 s | PDF: LLaDA2.1 Mini on RTX 3090 report |
|---|
| RTX 4090 | 8-bit | 32K | 298 tok/s | 0.1 s | PDF: LLaDA2.1 Mini on RTX 4090 report |
|---|
| Radeon AI PRO R9700 | 8-bit | 32K | 173 tok/s | 0.2 s | PDF: LLaDA2.1 Mini on Radeon AI PRO R9700 report |
|---|
| RTX 5090 | 8-bit | 32K | 414 tok/s | 0.1 s | PDF: LLaDA2.1 Mini on RTX 5090 report |
|---|
| 2× RTX 3090 | 8-bit | 32K | 284 tok/s | 0.1 s | PDF: LLaDA2.1 Mini on 2× RTX 3090 report |
|---|
| 2× RTX 4090 | 8-bit | 32K | 298 tok/s | 0.1 s | PDF: LLaDA2.1 Mini on 2× RTX 4090 report |
|---|
| RTX PRO 5000 Blackwell 48 GB | 8-bit | 32K | 355 tok/s | 0.1 s | PDF: LLaDA2.1 Mini on RTX PRO 5000 Blackwell 48 GB report |
|---|
| RTX 6000 Ada | 8-bit | 32K | 289 tok/s | 0.1 s | PDF: LLaDA2.1 Mini on RTX 6000 Ada report |
|---|
| L40S | 8-bit | 32K | 269 tok/s | 0.1 s | PDF: LLaDA2.1 Mini on L40S report |
|---|
| 2× RTX 5090 | 8-bit | 32K | 414 tok/s | 0.1 s | PDF: LLaDA2.1 Mini on 2× RTX 5090 report |
|---|
| 4× RTX 3090 | 8-bit | 32K | 284 tok/s | 0.1 s | PDF: LLaDA2.1 Mini on 4× RTX 3090 report |
|---|
| RTX PRO 6000 Blackwell | 8-bit | 32K | 414 tok/s | 0.1 s | PDF: LLaDA2.1 Mini on RTX PRO 6000 Blackwell report |
|---|
| Mac mini M4 16 GB | 3-bit | 32K | 101 tok/s | 4.0 s | PDF: LLaDA2.1 Mini on Mac mini M4 16 GB report |
|---|
| Mac mini M4 24 GB | 6-bit | 32K | 68 tok/s | 4.0 s | PDF: LLaDA2.1 Mini on Mac mini M4 24 GB report |
|---|
| Mac mini M4 32 GB | 8-bit | 32K | 55 tok/s | 4.0 s | PDF: LLaDA2.1 Mini on Mac mini M4 32 GB report |
|---|
| Mac mini M4 Pro 24 GB | 6-bit | 32K | 124 tok/s | 2.0 s | PDF: LLaDA2.1 Mini on Mac mini M4 Pro 24 GB report |
|---|
| Mac mini M4 Pro 48 GB | 8-bit | 32K | 104 tok/s | 2.0 s | PDF: LLaDA2.1 Mini on Mac mini M4 Pro 48 GB report |
|---|
| Mac mini M4 Pro 64 GB | 8-bit | 32K | 104 tok/s | 2.0 s | PDF: LLaDA2.1 Mini on Mac mini M4 Pro 64 GB report |
|---|
| M4 Max 128 GB | 8-bit | 32K | 153 tok/s | 1.0 s | PDF: LLaDA2.1 Mini on M4 Max 128 GB report |
|---|
| M5 Max 128 GB | 8-bit | 32K | 164 tok/s | 0.3 s | PDF: LLaDA2.1 Mini on M5 Max 128 GB report |
|---|
| M3 Ultra 96 GB | 8-bit | 32K | 177 tok/s | 0.6 s | PDF: LLaDA2.1 Mini on M3 Ultra 96 GB report |
|---|
| M3 Ultra 256 GB | 8-bit | 32K | 177 tok/s | 0.6 s | PDF: LLaDA2.1 Mini on M3 Ultra 256 GB report |
|---|
| M3 Ultra 512 GB | 8-bit | 32K | 177 tok/s | 0.6 s | PDF: LLaDA2.1 Mini on M3 Ultra 512 GB report |
|---|
| M5 Ultra 512 GB | 8-bit | 32K | 210 tok/s | 0.2 s | PDF: LLaDA2.1 Mini on M5 Ultra 512 GB report |
|---|
| Ryzen AI Max+ 395 64 GB | 8-bit | 32K | 85 tok/s | 0.6 s | PDF: LLaDA2.1 Mini on Ryzen AI Max+ 395 64 GB report |
|---|
| Ryzen AI Max+ 395 128 GB | 8-bit | 32K | 85 tok/s | 0.6 s | PDF: LLaDA2.1 Mini on Ryzen AI Max+ 395 128 GB report |
|---|
| RTX Spark | 8-bit | 32K | 118 tok/s | 0.3 s | PDF: LLaDA2.1 Mini on RTX Spark report |
|---|
| DGX Spark | 8-bit | 32K | 109 tok/s | 0.4 s | PDF: LLaDA2.1 Mini on DGX Spark report |
|---|
| Dual DGX Spark | 8-bit | 32K | 109 tok/s | 0.2 s | PDF: LLaDA2.1 Mini on Dual DGX Spark report |
|---|
| DGX Station GB300 | 8-bit | 32K | 664 tok/s | 0.1 s | PDF: LLaDA2.1 Mini on DGX Station GB300 report |
|---|
| 2× RTX PRO 6000 Blackwell | 8-bit | 32K | 414 tok/s | 0.1 s | PDF: LLaDA2.1 Mini on 2× RTX PRO 6000 Blackwell report |
|---|
| 4× RTX PRO 6000 Blackwell | 8-bit | 32K | 414 tok/s | 0.1 s | PDF: LLaDA2.1 Mini on 4× RTX PRO 6000 Blackwell report |
|---|
| 8× RTX PRO 6000 Blackwell | 8-bit | 32K | 414 tok/s | 0.1 s | PDF: LLaDA2.1 Mini on 8× RTX PRO 6000 Blackwell report |
|---|
| A100 80 GB SXM | 8-bit | 32K | 441 tok/s | 0.1 s | PDF: LLaDA2.1 Mini on A100 80 GB SXM report |
|---|
| H100 SXM | 8-bit | 32K | 541 tok/s | 0.1 s | PDF: LLaDA2.1 Mini on H100 SXM report |
|---|
| 4× H200 NVL | 8-bit | 32K | 605 tok/s | 0.1 s | PDF: LLaDA2.1 Mini on 4× H200 NVL report |
|---|
| 8× H200 NVL | 8-bit | 32K | 605 tok/s | 0.1 s | PDF: LLaDA2.1 Mini on 8× H200 NVL report |
|---|