George Hotz's company, tiny corp, has launched the tinybox, a $15,000 personal AI computer designed for local model training and inference. The tinybox boasts 738 FP16 TFLOPS and 144 GB of GPU RAM, capable of running a 65B LLaMA model out of the box. Hotz's approach with the tinygrad framework emphasizes a RISC philosophy for efficiency and avoids Turing-complete kernels, aiming to compete with established players like NVIDIA by focusing on developer experience and optimizing for off-the-shelf hardware. AI
RANK_REASON Launch of a new AI hardware product by a notable figure in the AI community.
Read on Latent Space Podcast →
- AMD EPYC
- AMD RX 7900 XTX
- Apple Silicon M1
- Apple Silicon M2
- Comma.ai
- CUDA
- George Hotz
- ggml
- LLaMA
- Mojo
- NVIDIA
- PrimTorch
- Raspberry Pi
- AMD Ryzen
- tinybox
- tiny corp
- tinygrad
- XLA
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →