| RTX 4060 | Too big | | | | PDF: DeepSeek V4 Flash on RTX 4060 report |
|---|
| RTX 5060 | Too big | | | | PDF: DeepSeek V4 Flash on RTX 5060 report |
|---|
| RTX 3070 | Too big | | | | PDF: DeepSeek V4 Flash on RTX 3070 report |
|---|
| RTX 3080 10 GB | Too big | | | | PDF: DeepSeek V4 Flash on RTX 3080 10 GB report |
|---|
| RTX 3060 12 GB | Too big | | | | PDF: DeepSeek V4 Flash on RTX 3060 12 GB report |
|---|
| Arc B580 | Too big | | | | PDF: DeepSeek V4 Flash on Arc B580 report |
|---|
| RTX 4070 | Too big | | | | PDF: DeepSeek V4 Flash on RTX 4070 report |
|---|
| RTX 4070 Super | Too big | | | | PDF: DeepSeek V4 Flash on RTX 4070 Super report |
|---|
| RTX 5070 | Too big | | | | PDF: DeepSeek V4 Flash on RTX 5070 report |
|---|
| RTX 4060 Ti 16 GB | Too big | | | | PDF: DeepSeek V4 Flash on RTX 4060 Ti 16 GB report |
|---|
| RTX 5060 Ti 16 GB | Too big | | | | PDF: DeepSeek V4 Flash on RTX 5060 Ti 16 GB report |
|---|
| Arc A770 16 GB | Too big | | | | PDF: DeepSeek V4 Flash on Arc A770 16 GB report |
|---|
| Radeon RX 9070 XT | Too big | | | | PDF: DeepSeek V4 Flash on Radeon RX 9070 XT report |
|---|
| RTX 4070 Ti Super | Too big | | | | PDF: DeepSeek V4 Flash on RTX 4070 Ti Super report |
|---|
| RTX 4080 Super | Too big | | | | PDF: DeepSeek V4 Flash on RTX 4080 Super report |
|---|
| RTX 5070 Ti | Too big | | | | PDF: DeepSeek V4 Flash on RTX 5070 Ti report |
|---|
| RTX 5080 | Too big | | | | PDF: DeepSeek V4 Flash on RTX 5080 report |
|---|
| Radeon RX 7900 XTX | Too big | | | | PDF: DeepSeek V4 Flash on Radeon RX 7900 XTX report |
|---|
| RTX 3090 | Too big | | | | PDF: DeepSeek V4 Flash on RTX 3090 report |
|---|
| RTX 4090 | Too big | | | | PDF: DeepSeek V4 Flash on RTX 4090 report |
|---|
| Radeon AI PRO R9700 | Too big | | | | PDF: DeepSeek V4 Flash on Radeon AI PRO R9700 report |
|---|
| RTX 5090 | Too big | | | | PDF: DeepSeek V4 Flash on RTX 5090 report |
|---|
| 2× RTX 3090 | Too big | | | | PDF: DeepSeek V4 Flash on 2× RTX 3090 report |
|---|
| 2× RTX 4090 | Too big | | | | PDF: DeepSeek V4 Flash on 2× RTX 4090 report |
|---|
| RTX PRO 5000 Blackwell 48 GB | Too big | | | | PDF: DeepSeek V4 Flash on RTX PRO 5000 Blackwell 48 GB report |
|---|
| RTX 6000 Ada | Too big | | | | PDF: DeepSeek V4 Flash on RTX 6000 Ada report |
|---|
| L40S | Too big | | | | PDF: DeepSeek V4 Flash on L40S report |
|---|
| 2× RTX 5090 | Too big | | | | PDF: DeepSeek V4 Flash on 2× RTX 5090 report |
|---|
| 4× RTX 3090 | Too big | | | | PDF: DeepSeek V4 Flash on 4× RTX 3090 report |
|---|
| RTX PRO 6000 Blackwell | Too big | | | | PDF: DeepSeek V4 Flash on RTX PRO 6000 Blackwell report |
|---|
| Mac mini M4 16 GB | Too big | | | | PDF: DeepSeek V4 Flash on Mac mini M4 16 GB report |
|---|
| Mac mini M4 24 GB | Too big | | | | PDF: DeepSeek V4 Flash on Mac mini M4 24 GB report |
|---|
| Mac mini M4 32 GB | Too big | | | | PDF: DeepSeek V4 Flash on Mac mini M4 32 GB report |
|---|
| Mac mini M4 Pro 24 GB | Too big | | | | PDF: DeepSeek V4 Flash on Mac mini M4 Pro 24 GB report |
|---|
| Mac mini M4 Pro 48 GB | Too big | | | | PDF: DeepSeek V4 Flash on Mac mini M4 Pro 48 GB report |
|---|
| Mac mini M4 Pro 64 GB | Too big | | | | PDF: DeepSeek V4 Flash on Mac mini M4 Pro 64 GB report |
|---|
| M4 Max 128 GB | Too big | | | | PDF: DeepSeek V4 Flash on M4 Max 128 GB report |
|---|
| M5 Max 128 GB | Too big | | | | PDF: DeepSeek V4 Flash on M5 Max 128 GB report |
|---|
| M3 Ultra 96 GB | Too big | | | | PDF: DeepSeek V4 Flash on M3 Ultra 96 GB report |
|---|
| M3 Ultra 256 GB | FP4 + FP8 | 1M | 24 tok/s | 7.7 s | PDF: DeepSeek V4 Flash on M3 Ultra 256 GB report |
|---|
| M3 Ultra 512 GB | FP4 + FP8 | 1M | 24 tok/s | 7.7 s | PDF: DeepSeek V4 Flash on M3 Ultra 512 GB report |
|---|
| M5 Ultra 512 GB | FP4 + FP8 | 1M | 33 tok/s | 2.4 s | PDF: DeepSeek V4 Flash on M5 Ultra 512 GB report |
|---|
| Ryzen AI Max+ 395 64 GB | Too big | | | | PDF: DeepSeek V4 Flash on Ryzen AI Max+ 395 64 GB report |
|---|
| Ryzen AI Max+ 395 128 GB | Too big | | | | PDF: DeepSeek V4 Flash on Ryzen AI Max+ 395 128 GB report |
|---|
| RTX Spark | 2-bit | 1M | 28 tok/s | 2.8 s | PDF: DeepSeek V4 Flash on RTX Spark report |
|---|
| DGX Spark | 2-bit | 1M | 25 tok/s | 2.8 s | PDF: DeepSeek V4 Flash on DGX Spark report |
|---|
| Dual DGX Spark | FP4 + FP8 | 1M | 9.9 tok/s | 2.0 s | PDF: DeepSeek V4 Flash on Dual DGX Spark report |
|---|
| DGX Station GB300 | FP4 + FP8 | 1M | 157 tok/s | 0.2 s | PDF: DeepSeek V4 Flash on DGX Station GB300 report |
|---|
| 2× RTX PRO 6000 Blackwell | FP4 + FP8 | 1M | 57 tok/s | 0.4 s | PDF: DeepSeek V4 Flash on 2× RTX PRO 6000 Blackwell report |
|---|
| 4× RTX PRO 6000 Blackwell | FP4 + FP8 | 1M | 57 tok/s | 0.2 s | PDF: DeepSeek V4 Flash on 4× RTX PRO 6000 Blackwell report |
|---|
| 8× RTX PRO 6000 Blackwell | FP4 + FP8 | 1M | 57 tok/s | 0.1 s | PDF: DeepSeek V4 Flash on 8× RTX PRO 6000 Blackwell report |
|---|
| A100 80 GB SXM | Too big | | | | PDF: DeepSeek V4 Flash on A100 80 GB SXM report |
|---|
| H100 SXM | Too big | | | | PDF: DeepSeek V4 Flash on H100 SXM report |
|---|
| 4× H200 NVL | FP4 + FP8 | 1M | 122 tok/s | 0.2 s | PDF: DeepSeek V4 Flash on 4× H200 NVL report |
|---|
| 8× H200 NVL | FP4 + FP8 | 1M | 122 tok/s | 0.1 s | PDF: DeepSeek V4 Flash on 8× H200 NVL report |
|---|