SingVL_S1_4B released
The story so far
Ant inclusionAI and Hugging Face have released a multimodal decision-making model SingVL_S1_4B based on Qwen3.5, which can answer named questions based on text or JSON and up to four images. SingVL_S1_4B performs excellently on 43 text datasets and 11 visual datasets, supporting Python 3.12 and PyTorch inference. SingVL_S1_4B is a multimodal decision-making model based on Qwen3.5, capable of processing text or JSON inputs and supporting up to four image inputs to answer named questions. Each question's answer is scored by a single Transformers forward pass. The newly released SingVL-4B GGUF is a 4B parameter version of SingVL_S1_4B, using the llama.cpp adapter, with a default context size of 4096 tokens, and achieving scores of 69.76 and 73.94 in the Text and Vision evaluations, respectively.
AI-written from the reports · Updated 2 days ago
Coverage timeline
Follow the coverage to see every side of the story.
- Ant Group inclusionAI · Hugging Face new modelsinclusionAI/SingVL_S1_4B_GGUF releases the SingVL-4B GGUF multimodal decision model
SingVL-4B GGUF is the GGUF version of the 4B parameter multimodal decision-making model Sing VL S1 based on Qwen3.5, which can answer named entity questions with text or JSON and up to four images, and uses a full forward pass scoring option, scoring 69.76 in the Text evaluation and 73.94 in the Vision evaluation. The model uses the llama.cpp adapter, with a default context size of 4096 tokens, supporting text and image input.
- Ant Group inclusionAI · Hugging Face new modelsinclusionAI/SingVL_S1_4B released: A multimodal decision-making model based on Qwen3.5
Sing VL S1 is a multimodal decision-making model based on Qwen3.5, capable of answering named entity questions with text or JSON and up to four images, scoring options for each question using a single Transformers forward pass, performing excellently on 43 text datasets and 11 visual datasets, supporting Python 3.12 and PyTorch inference.
Heat over time
- Now
- 3
- Peak
- 1012 Nov, 11:00
- 24h change
- -49%
Hover or tap the chart to see each hour; use the arrow keys on a keyboard.