Looks like geohot is now advertising Team Green and Team Red options with the latter being $10k cheaper.
tinybox green - 6x NVIDIA RTX 4090 ($25k)
You came here to do ML and you want it to just work. You like checking out the latest open source ML stuff on GitHub. gpt-fast. You want
your Attention to be CUDA quality FlashAttention. You want FP8. A solid box for the ML researcher. A solid box for the tinygrad developer. A solid
box for everyone. It's just a little expensive.
tinybox red - 6x AMD 7900XTX ($15k)
You came here for the hardware.
You want to be a part of the journey. Make AMD great, with or without their help. Sure, it works for ML, mostly. Just maybe you have to reboot it sometimes. tinygrad
does work well enough to get AMD on MLPerf at least. You buy the red box because you want to mess with kernel drivers and shader
engines. You know what a warp is. You like that you can see the MMIO with umr.
RDNA3 is documented! You want to get every bit of perf out of the metal.
The specs are similar to green, except it's $10k cheaper.
tinybox green - 6x NVIDIA RTX 4090 ($25k)
You came here to do ML and you want it to just work. You like checking out the latest open source ML stuff on GitHub. gpt-fast. You want your Attention to be CUDA quality FlashAttention. You want FP8. A solid box for the ML researcher. A solid box for the tinygrad developer. A solid box for everyone. It's just a little expensive.
tinybox red - 6x AMD 7900XTX ($15k)
You came here for the hardware.
You want to be a part of the journey. Make AMD great, with or without their help. Sure, it works for ML, mostly. Just maybe you have to reboot it sometimes. tinygrad does work well enough to get AMD on MLPerf at least. You buy the red box because you want to mess with kernel drivers and shader engines. You know what a warp is. You like that you can see the MMIO with umr. RDNA3 is documented! You want to get every bit of perf out of the metal.
The specs are similar to green, except it's $10k cheaper.