| RTX 4060 | 6-bit | 32K | 174 tok/s | 0.4 s | PDF: LFM2.5 8B A1B on RTX 4060 report |
|---|
| RTX 5060 | 6-bit | 32K | 247 tok/s | 0.3 s | PDF: LFM2.5 8B A1B on RTX 5060 report |
|---|
| RTX 3070 | 6-bit | 32K | 247 tok/s | 0.3 s | PDF: LFM2.5 8B A1B on RTX 3070 report |
|---|
| RTX 3080 10 GB | 8-bit | 28K | 291 tok/s | 0.2 s | PDF: LFM2.5 8B A1B on RTX 3080 10 GB report |
|---|
| RTX 3060 12 GB | 8-bit | 125K | 177 tok/s | 0.5 s | PDF: LFM2.5 8B A1B on RTX 3060 12 GB report |
|---|
| Arc B580 | 8-bit | 125K | 142 tok/s | 0.3 s | PDF: LFM2.5 8B A1B on Arc B580 report |
|---|
| RTX 4070 | 8-bit | 125K | 225 tok/s | 0.2 s | PDF: LFM2.5 8B A1B on RTX 4070 report |
|---|
| RTX 4070 Super | 8-bit | 125K | 225 tok/s | 0.2 s | PDF: LFM2.5 8B A1B on RTX 4070 Super report |
|---|
| RTX 5070 | 8-bit | 125K | 270 tok/s | 0.2 s | PDF: LFM2.5 8B A1B on RTX 5070 report |
|---|
| RTX 4060 Ti 16 GB | 8-bit | 125K | 149 tok/s | 0.3 s | PDF: LFM2.5 8B A1B on RTX 4060 Ti 16 GB report |
|---|
| RTX 5060 Ti 16 GB | 8-bit | 125K | 207 tok/s | 0.3 s | PDF: LFM2.5 8B A1B on RTX 5060 Ti 16 GB report |
|---|
| Arc A770 16 GB | 8-bit | 125K | 161 tok/s | 0.3 s | PDF: LFM2.5 8B A1B on Arc A770 16 GB report |
|---|
| Radeon RX 9070 XT | 8-bit | 125K | 203 tok/s | 0.2 s | PDF: LFM2.5 8B A1B on Radeon RX 9070 XT report |
|---|
| RTX 4070 Ti Super | 8-bit | 125K | 270 tok/s | 0.1 s | PDF: LFM2.5 8B A1B on RTX 4070 Ti Super report |
|---|
| RTX 4080 Super | 8-bit | 125K | 285 tok/s | 0.1 s | PDF: LFM2.5 8B A1B on RTX 4080 Super report |
|---|
| RTX 5070 Ti | 8-bit | 125K | 319 tok/s | 0.1 s | PDF: LFM2.5 8B A1B on RTX 5070 Ti report |
|---|
| RTX 5080 | 8-bit | 125K | 331 tok/s | 0.1 s | PDF: LFM2.5 8B A1B on RTX 5080 report |
|---|
| Radeon RX 7900 XTX | 8-bit | 125K | 250 tok/s | 0.3 s | PDF: LFM2.5 8B A1B on Radeon RX 7900 XTX report |
|---|
| RTX 3090 | 8-bit | 125K | 327 tok/s | 0.2 s | PDF: LFM2.5 8B A1B on RTX 3090 report |
|---|
| RTX 4090 | 8-bit | 125K | 339 tok/s | 0.1 s | PDF: LFM2.5 8B A1B on RTX 4090 report |
|---|
| Radeon AI PRO R9700 | 8-bit | 125K | 203 tok/s | 0.2 s | PDF: LFM2.5 8B A1B on Radeon AI PRO R9700 report |
|---|
| RTX 5090 | 8-bit | 125K | 437 tok/s | 0.1 s | PDF: LFM2.5 8B A1B on RTX 5090 report |
|---|
| 2× RTX 3090 | 8-bit | 125K | 327 tok/s | 0.1 s | PDF: LFM2.5 8B A1B on 2× RTX 3090 report |
|---|
| 2× RTX 4090 | 8-bit | 125K | 339 tok/s | 0.1 s | PDF: LFM2.5 8B A1B on 2× RTX 4090 report |
|---|
| RTX PRO 5000 Blackwell 48 GB | 8-bit | 125K | 389 tok/s | 0.1 s | PDF: LFM2.5 8B A1B on RTX PRO 5000 Blackwell 48 GB report |
|---|
| RTX 6000 Ada | 8-bit | 125K | 331 tok/s | 0.1 s | PDF: LFM2.5 8B A1B on RTX 6000 Ada report |
|---|
| L40S | 8-bit | 125K | 313 tok/s | 0.1 s | PDF: LFM2.5 8B A1B on L40S report |
|---|
| 2× RTX 5090 | 8-bit | 125K | 437 tok/s | 0.1 s | PDF: LFM2.5 8B A1B on 2× RTX 5090 report |
|---|
| 4× RTX 3090 | 8-bit | 125K | 327 tok/s | 0.1 s | PDF: LFM2.5 8B A1B on 4× RTX 3090 report |
|---|
| RTX PRO 6000 Blackwell | 8-bit | 125K | 437 tok/s | 0.1 s | PDF: LFM2.5 8B A1B on RTX PRO 6000 Blackwell report |
|---|
| Mac mini M4 16 GB | 8-bit | 96K | 71 tok/s | 3.8 s | PDF: LFM2.5 8B A1B on Mac mini M4 16 GB report |
|---|
| Mac mini M4 24 GB | 8-bit | 125K | 71 tok/s | 3.8 s | PDF: LFM2.5 8B A1B on Mac mini M4 24 GB report |
|---|
| Mac mini M4 32 GB | 8-bit | 125K | 71 tok/s | 3.8 s | PDF: LFM2.5 8B A1B on Mac mini M4 32 GB report |
|---|
| Mac mini M4 Pro 24 GB | 8-bit | 125K | 123 tok/s | 1.9 s | PDF: LFM2.5 8B A1B on Mac mini M4 Pro 24 GB report |
|---|
| Mac mini M4 Pro 48 GB | 8-bit | 125K | 123 tok/s | 1.9 s | PDF: LFM2.5 8B A1B on Mac mini M4 Pro 48 GB report |
|---|
| Mac mini M4 Pro 64 GB | 8-bit | 125K | 123 tok/s | 1.9 s | PDF: LFM2.5 8B A1B on Mac mini M4 Pro 64 GB report |
|---|
| M4 Max 128 GB | 8-bit | 125K | 168 tok/s | 1.0 s | PDF: LFM2.5 8B A1B on M4 Max 128 GB report |
|---|
| M5 Max 128 GB | 8-bit | 125K | 176 tok/s | 0.3 s | PDF: LFM2.5 8B A1B on M5 Max 128 GB report |
|---|
| M3 Ultra 96 GB | 8-bit | 125K | 187 tok/s | 0.5 s | PDF: LFM2.5 8B A1B on M3 Ultra 96 GB report |
|---|
| M3 Ultra 256 GB | 8-bit | 125K | 187 tok/s | 0.5 s | PDF: LFM2.5 8B A1B on M3 Ultra 256 GB report |
|---|
| M3 Ultra 512 GB | 8-bit | 125K | 187 tok/s | 0.5 s | PDF: LFM2.5 8B A1B on M3 Ultra 512 GB report |
|---|
| M5 Ultra 512 GB | 8-bit | 125K | 212 tok/s | 0.2 s | PDF: LFM2.5 8B A1B on M5 Ultra 512 GB report |
|---|
| Ryzen AI Max+ 395 64 GB | 8-bit | 125K | 110 tok/s | 0.6 s | PDF: LFM2.5 8B A1B on Ryzen AI Max+ 395 64 GB report |
|---|
| Ryzen AI Max+ 395 128 GB | 8-bit | 125K | 110 tok/s | 0.6 s | PDF: LFM2.5 8B A1B on Ryzen AI Max+ 395 128 GB report |
|---|
| RTX Spark | 8-bit | 125K | 154 tok/s | 0.2 s | PDF: LFM2.5 8B A1B on RTX Spark report |
|---|
| DGX Spark | 8-bit | 125K | 143 tok/s | 0.2 s | PDF: LFM2.5 8B A1B on DGX Spark report |
|---|
| Dual DGX Spark | 8-bit | 125K | 143 tok/s | 0.1 s | PDF: LFM2.5 8B A1B on Dual DGX Spark report |
|---|
| DGX Station GB300 | 8-bit | 125K | 605 tok/s | 0.1 s | PDF: LFM2.5 8B A1B on DGX Station GB300 report |
|---|
| 2× RTX PRO 6000 Blackwell | 8-bit | 125K | 437 tok/s | 0.1 s | PDF: LFM2.5 8B A1B on 2× RTX PRO 6000 Blackwell report |
|---|
| 4× RTX PRO 6000 Blackwell | 8-bit | 125K | 437 tok/s | 0.1 s | PDF: LFM2.5 8B A1B on 4× RTX PRO 6000 Blackwell report |
|---|
| 8× RTX PRO 6000 Blackwell | 8-bit | 125K | 437 tok/s | 0.1 s | PDF: LFM2.5 8B A1B on 8× RTX PRO 6000 Blackwell report |
|---|
| A100 80 GB SXM | 8-bit | 125K | 458 tok/s | 0.1 s | PDF: LFM2.5 8B A1B on A100 80 GB SXM report |
|---|
| H100 SXM | 8-bit | 125K | 528 tok/s | 0.1 s | PDF: LFM2.5 8B A1B on H100 SXM report |
|---|
| 4× H200 NVL | 8-bit | 125K | 569 tok/s | 0.1 s | PDF: LFM2.5 8B A1B on 4× H200 NVL report |
|---|
| 8× H200 NVL | 8-bit | 125K | 569 tok/s | 0.1 s | PDF: LFM2.5 8B A1B on 8× H200 NVL report |
|---|