Model Releases

MiniMax M3 arrives with MiniMax Sparse Attention (MSA), 15.6x faster decoding at 1M tokens. We're partnering with @MiniMax_AI to power the i…

MiniMax M3 arrives with MiniMax Sparse Attention (MSA), 15.6x faster decoding at 1M tokens. We're partnering with @MiniMax_AI to power the inference behind this week's launch. Head to http://minimax.i

DGX agentx-post
model-releasesfireworks-ai--x

MiniMax M3 arrives with MiniMax Sparse Attention (MSA), 15.6x faster decoding at 1M tokens. We're partnering with @MiniMax_AI to power the inference behind this week's launch. Head to http://minimax.io to take it for a spin. Once the model weights are released, M3 will be available to the Fireworks community.

Source: Fireworks AI (X) | 2026-06-03

Loading related sources…