Skip to content

Qwen3 8B

Qwen/Qwen3-8B
Open Source · chat · open-weights
GA Alert me on changes
Context
131.1K
Max output
Input $/1M
$0.05
Output $/1M
$0.40
Modalities
text
Released
27 Apr 2025
License: apache-2.0 · Qwen/Qwen3-8B
AI summary
● machine-written

Qwen3 8B: Open-weights 8B parameter chat model

Qwen3 8B is an open-weights dense 8.2B parameter causal language model from Alibaba's Qwen series, designed for reasoning-heavy tasks and efficient dialogue. Released April 2025, it is available under the Apache 2.0 license with open access to weights. The model supports a 131,072 token context window and is suitable for both local deployment and API-based inference.

What's new
  • 8.2B parameter model optimized for reasoning and dialogue tasks
  • 131,072 token context window for extended context handling
  • Available through multiple inference providers including nscale and Featherless AI
  • Supports tool calling and structured output capabilities
  • Apache 2.0 licensed for open-source deployment
Best for
Dialogue and conversational applicationsReasoning-heavy task processingLocal and edge deployment scenariosTool-calling and agent workflows
Sources

Source: https://huggingface.co/Qwen/Qwen3-8B