Activefrontierllm Open Source

Qwen1.5 110B

by Alibaba· Released February 2024· Cutoff September 2023

Qwen1.5 110B is a large language model with 110 billion parameters, part of Alibaba's Qwen1.5 series. It excels in multilingual tasks, particularly in Chinese and English, and supports a 32K token context window. As the largest model in the Qwen1.5 lineup, it offers strong performance across a wide range of NLP benchmarks.

Official Site API Docs 🤗 Hugging Face 📄 Research Paper

Input cost

Free (open source)

Output cost

Free (open source)

Context window

32K tokens

Max output

8192 tokens

Modalities

text

Parameters

110B

License

Apache-2.0

Capabilities

Function CallingCode GenerationMultilingual SupportLong Context UnderstandingStreamingJSON Mode

Best For

Complex multilingual tasks requiring deep reasoning and long context understanding.

Strengths

Strong performance on multilingual benchmarks, especially Chinese and English
Large 110B parameter count for high-quality outputs
Supports 32K token context window
Open source with permissive license
Good at code generation and mathematical reasoning

Limitations

Requires significant computational resources for inference
Not multimodal (text-only)
May have slower inference compared to smaller models
Knowledge cutoff may not be as recent as some newer models

Use Cases

Multilingual customer support chatbots

Code generation and debugging assistance

Long document summarization and analysis

Complex reasoning tasks in finance or law

Content creation in multiple languages

Educational tutoring and question answering

Research and data analysis

Improvements Over Previous Model

Increased parameter count from 72B (Qwen 72B) to 110B
Context window expanded from 8K to 32K tokens
Improved multilingual performance, especially in non-English languages
Enhanced code generation capabilities with better HumanEval scores
Introduced function calling support
Better alignment with human preferences through improved RLHF

Back to all models

Activefrontierllm Open Source

Qwen1.5 110B

by Alibaba· Released February 2024· Cutoff September 2023

Official Site API Docs 🤗 Hugging Face 📄 Research Paper

Input cost

Free (open source)

Output cost

Free (open source)

Context window

32K tokens

Max output

8192 tokens

Modalities

text

Parameters

110B

License

Apache-2.0

Capabilities

Function CallingCode GenerationMultilingual SupportLong Context UnderstandingStreamingJSON Mode

Best For

Complex multilingual tasks requiring deep reasoning and long context understanding.

Strengths

Strong performance on multilingual benchmarks, especially Chinese and English
Large 110B parameter count for high-quality outputs
Supports 32K token context window
Open source with permissive license
Good at code generation and mathematical reasoning

Limitations

Requires significant computational resources for inference
Not multimodal (text-only)
May have slower inference compared to smaller models
Knowledge cutoff may not be as recent as some newer models

Use Cases

Multilingual customer support chatbots

Code generation and debugging assistance

Long document summarization and analysis

Complex reasoning tasks in finance or law

Content creation in multiple languages

Educational tutoring and question answering

Research and data analysis

Improvements Over Previous Model

Increased parameter count from 72B (Qwen 72B) to 110B
Context window expanded from 8K to 32K tokens
Improved multilingual performance, especially in non-English languages
Enhanced code generation capabilities with better HumanEval scores
Introduced function calling support
Better alignment with human preferences through improved RLHF

Back to all models