@modal: Are we going to be compute constrained for another decade? What are the tokenomics of Kimi K3? What’s holding up the AM…
Summary
SemiAnalysis founder Dylan Patel will speak at the Runtime event to discuss compute constraints, Kimi K3 tokenomics, and AMD supply chain issues. Applications to attend are open.
View Cached Full Text
Cached at: 08/08/26, 11:08 AM
Are we going to be compute constrained for another decade? What are the tokenomics of Kimi K3? What’s holding up the AMD supply chain?
Founder and CEO of @SemiAnalysis_, @dylan522p, is joining us on stage at Runtime to answer all this and more.
Apply to attend. https://t.co/p6cWTrV1WD
Similar Articles
@modal: You can now run Kimi K3 in Codex on Modal. K3 leads open models on agentic coding benchmarks, with native vision and a …
Kimi K3, an open model that leads agentic coding benchmarks with native vision and a 1M-token context window, is now available to run in Codex on Modal via its Shared Endpoint.
On Kimi K3: Its Capabilities And Related Discontents (70 minute read)
Kimi K3 is a 2.8T parameter open model from Moonshot AI, showing strong benchmark performance but likely over-optimized and lagging behind top closed models by months. It is distilled from Claude and its release may precede an IPO.
@wafer_ai: BREAKING We're on Hacker News again we figured out how to serve Kimi K3 at 3.8x higher throughput and 71% lower cost on…
Wafer announces that it can serve Kimi K3 on AMD MI355X at 3.8x higher throughput and 71% lower cost than on B200 nodes, arguing that AMD's large VRAM and software support make it the best performance-per-dollar choice for frontier models.
@Modular: Our kernel team has been deep in MiniMax M3 all week. The 1M-token context and native multimodality make it a hard mode…
Modular's kernel team is optimizing serving for MiniMax M3's 1M-token context and native multimodality, with open weights dropping soon for immediate deployment on Modular.
@thealexker: underrated gems in Kimi-K3 release: > an early K3 wrote the majority of the kernels in the late development stages > it…
Kimi.ai released Kimi K3, a 2.8 trillion parameter multimodal model with 1 million context, featuring novel Delta Attention and Attention Residuals, and a self-optimizing stack including MiniTriton compiler. The model achieves up to 6.3x faster decoding and ~25% higher training efficiency.