DeepSeek-V4-Pro-0813 available now on Fireworks

Model Library/Qwen/Qwen3.8 27B
Quen Logo Mark

Qwen3.8 27B

Ready
Deploy on Demand
model path:accounts/fireworks/models/qwen3p8-27b

Qwen3.8-27B: 27B-parameter vision-language model from Qwen with hybrid linear/full attention (4:1 interval) and 262K context.

Qwen3.8 27B API Features

On-demand Deployment

Docs

On-demand deployments allow you to use Qwen3.8 27B on dedicated GPUs with Fireworks' high-performance serving stack with high reliability and no rate limits.

Metadata

State
Ready
Created on
8/14/2026
Kind
Base model
Provider
Qwen
Hugging Face
Qwen/Qwen3.8-27B

Specification

Calibrated
No
Mixture-of-Experts
No
Parameters
27.3B

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