Model Library/Qwen3 32B
qwen/qwen3-32b-fp8

Qwen3 32B

qwen/qwen3-32b-fp8
Achieves effective integration of inference and non-inference modes, allowing seamless switching between modes during conversations. Its inference capability matches that of QwQ-32B with a smaller parameter size, and its general capabilities significantly surpass those of Qwen2.5-14B, reaching the state-of-the-art (SOTA) level among models of the same scale.

Características

Implementaciones bajo demanda

Documentación

On-demand deployments allow you to use qwen/qwen3-32b-fp8 on dedicated GPUs with high-performance serving stack with high reliability and no rate limits.

Información

Proveedor
Qwen
Cuantización
fp8

Funcionalidad compatible

Longitud del contexto
40960
Salida máxima
20000
Serverless
No compatible
Reasoning
Compatible
Capacidades de entrada
text
Capacidades de salida
text