Skip to main content
Language modelActive

Virtuoso Large

Arcee AI

Released
June 30, 2025
Data date
September 8, 2026
Price
Historical rates under Costs
Input
Text
Output
Text

Virtuoso Large combines open 72B weights based on Qwen 2.5 72B with a 131K context. The weights use the Qwen Tongyi license, and GGUF quantizations are available.

Specifications and access

SpecificationValue and source
Weights
Open weightsSource
Access
LocalSource
Parameters
Context window
131,072 tokensSource
Release
2025-06-30Source
License
Qwen Tongyi LicenseSource
Parameters
72 BSource
Architecture
dense Qwen2ForCausalLM / Qwen2.5-72B, 80 layers, hidden size 8192, 64 attention heads and 8 KV headsSource
Input
TextSource
Output
TextSource
Languages
multilingualSource