Batch processing
Text generation models
Model |
URI |
Context |
Qwen 2.5 7B Instruct |
|
32,768 |
Qwen 2.5 72B Instruct |
|
16,384 |
QwQ 32B Instruct |
|
32,768 |
Llama 3.3 70B Instruct2 |
|
8,192 |
Llama 3.1 70B Instruct2 |
|
8,192 |
DeepSeek-R1 Distill Llama 70B |
|
8,192 |
Qwen2.5 32B Instruct |
|
32,768 |
DeepSeek-R1 Distill Qwen 32B |
|
32,768 |
phi-4 |
|
16,384 |
Gemma 3 1B it |
|
32,768 |
Gemma 3 4B it |
|
131,072 |
Gemma 3 12B it |
|
65,536 |
Gemma 3 27B it |
|
32,768 |
Qwen3 0.6B |
|
32,768 |
Qwen3 1.7B |
|
32,768 |
Qwen3 4B |
|
32,768 |
Qwen3 8B |
|
32,768 |
Qwen3 14B |
|
32,768 |
Qwen3 32B |
|
32,768 |
Qwen3 30B A3B |
|
32,768 |
Qwen3 235B A22B |
|
32,768 |
2 Llama was created by Meta. Meta is designated as an extremist organization and its activities are prohibited in Russia.
Multimodal models
Model |
URI |
Context |
Qwen2 VL 7BModel card |
|
4,096 |
Qwen2.5 VL 7BModel card |
|
4,096 |
Qwen 2.5 VL 32B InstructModel card |
|
4,096 |
DeepSeek VL2Model card |
|
4,096 |
DeepSeek VL2 TinyModel card |
|
4,096 |
Gemma 3 4B itModel card |
|
4,096 |
Gemma 3 12B itModel card |
|
4,096 |
Gemma 3 27B itModel card |
|
4,096 |