Qwen3 8B
qwen/qwen3-8b-fp8
Achieves effective integration of reasoning and non-reasoning modes, allowing seamless mode switching during conversations. Its reasoning capability reaches state-of-the-art (SOTA) performance among models of the same scale, and its general capabilities significantly outperform those of Qwen2.5-7B.
Features
On-demand Deployments
Docs
On-demand deployments allow you to use qwen/qwen3-8b-fp8 on dedicated GPUs with high-performance serving stack with high reliability and no rate limits.
Info
Provider
Qwen
Quantization
fp8
Supported Functionality
Context Length
128000
Max Output
20000
Serverless
Not supported
Input Capabilities
text
Output Capabilities
text