DeepSeek-VL2
General purposeMultimodal
DeepSeek has released a new version of their vision models. The models come in various small sizes and are all MoE models, which is unusual in this size range. The language models are trained solely for this model, which could be from experimentation when training DeepSeek V3.
Specs
Params1.0B, 2.8B, 4.5B
LicenseDeepSeek Model License
Similarity · VAIL
VAIL Fingerprint
056d:0710:0aac:0e82:1168:1774:32f4:5bdc
Explore other models with behavioral similarity to DeepSeek-VL2.
Adoption · Hugging Face
RAM @ 30d
Relative Adoption Metric: 0.00×. Below benchmark. Measured at 30 days.
Hugging Face Downloads
5.3K
last 30d
186.1K
all time
HF Likes
389
Relative Adoption Metric contextualizes downloads against the model's size bucket.
Related Models
