Llama 3.1 is a leading model launched by Meta, supporting up to 405B parameters, applicable in complex dialogues, multilingual translation, and data analysis.
128K
Llama 3.1 70B
llama3.1:70b
70b.description
128K
Llama 3.1 405B
llama3.1:405b
405b.description
128K
Code Llama 7B
codellama
Code Llama is an LLM focused on code generation and discussion, combining extensive programming language support, suitable for developer environments.
16K
Code Llama 13B
codellama:13b
13b.description
16K
Code Llama 34B
codellama:34b
34b.description
16K
Code Llama 70B
codellama:70b
70b.description
16K
QwQ 32B
qwq
QwQ is an experimental research model focused on improving AI reasoning capabilities.
128K
Qwen2.5 0.5B
qwen2.5:0.5b
0.5b.description
128K
Qwen2.5 1.5B
qwen2.5:1.5b
1.5b.description
128K
Qwen2.5 7B
qwen2.5
qwen2.5.description
128K
Qwen2.5 72B
qwen2.5:72b
72b.description
128K
Qwen2.5 7B
qwen2.5
qwen2.5.description
128K
CodeQwen1.5 7B
codeqwen
CodeQwen1.5 is a large language model trained on extensive code data, specifically designed to solve complex programming tasks.
64K
Qwen2 0.5B
qwen2:0.5b
0.5b.description
128K
Qwen2 1.5B
qwen2:1.5b
1.5b.description
128K
Qwen2 7B
qwen2
Qwen2 is Alibaba's next-generation large-scale language model, supporting diverse application needs with excellent performance.
128K
Qwen2 72B
qwen2:72b
72b.description
128K
Gemma 2 2B
gemma2:2b
2b.description
8K
Gemma 2 9B
gemma2
Gemma 2 is an efficient model launched by Google, covering a variety of application scenarios from small applications to complex data processing.
8K
Gemma 2 27B
gemma2:27b
27b.description
8K
CodeGemma 2B
codegemma:2b
2b.description
8K
CodeGemma 7B
codegemma
CodeGemma is a lightweight language model dedicated to various programming tasks, supporting rapid iteration and integration.
8K
Phi-3 3.8B
phi3
Phi-3 is a lightweight open model launched by Microsoft, suitable for efficient integration and large-scale knowledge reasoning.