Model Library/Fireworks/Qwen3.8 Flash Next FP4

Qwen3.8 Flash Next FP4

Ready

model path:accounts/fireworks/models/qwen3p8-flash-next-nvfp4

Qwen3.8-Flash-Next is an experimental Qwen4-architecture preview: a multimodal MoE with 125B parameters (6B active) plus 51B n-gram embeddings and native 262K context.

Qwen3.8 Flash Next FP4 API Features

On-demand Deployment

Docs

On-demand deployments allow you to use Qwen3.8 Flash Next FP4 on dedicated GPUs with Fireworks' high-performance serving stack with high reliability and no rate limits.

Metadata

State

Ready

Created on

8/27/2026

Kind

Base model

Provider

Fireworks

Hugging Face

Inferact/Qwen3.8-Flash-Next-NVFP4

Specification

Calibrated

Mixture-of-Experts

Yes

Parameters

118B

Supported Functionality

Fine-tuning

Not supported

Serverless

Not supported

Context Length

262k tokens

Function Calling

Supported

Embeddings

Not supported

Rerankers

Not supported

Support image input

Supported