An 8B hybrid reasoning model with 64K context, English and Chinese language support and sparse attention, released under Apache 2.0. These are explicitly marketed as on-device models, such as in their tech report, and fly under the radar because they're not challenging "frontier performance" like Qwen or DeepSeek.
Specs
Params8B
LicenseApache-2.0
Similarity · VAIL
VAIL Fingerprint
01a2:01fe:02c0:0486:066e:0a5c:1543:56bc
Explore other models with behavioral similarity to MiniCPM4.1-8B.
Adoption · Hugging Face
RAM @ 30d
Relative Adoption Metric: 0.00×. Below benchmark. Measured at 30 days.
Hugging Face Downloads
55.1K
last 30d
487.4K
all time
HF Likes
391
Relative Adoption Metric contextualizes downloads against the model's size bucket.
Related Models
