Is their hardware programming interface reasonable for implementing inference of frontier models: no quantization, several tera params?
BTW, how many many params open weight frontier models have? A few teras, 100s of teras?
loading story #49173059
Kimi-K3: 2.8T
Qwen3.8-Max: 2.4T
DeepSeek V4 Pro: 1.6T
DeepSeek V4 Flash: 284B
(all are total parameter counts, not active parameters)
loading story #49173902