Qwen3.8 Flash Next FP8
Readymodel path:accounts/fireworks/models/qwen3p8-flash-next-fp8
Qwen3.8-Flash-Next is an experimental Qwen4-architecture preview: multimodal MoE, 125B parameters (6B active) plus 51B n-gram embeddings, native 262K context.
On-demand deployments allow you to use Qwen3.8 Flash Next FP8 on dedicated GPUs with Fireworks' high-performance serving stack with high reliability and no rate limits.