Compact: 1 to 10 billion
Phi, Gemma, Llama 3 8B, Mistral 7B and most on-device and edge models. 82 models.
🇺🇸 United StatesGranite 3.0
IBM's third-generation open enterprise language models, from 2B to 8B parametersGeneral · Open weights · 2024
🇺🇸 United StatesNemotron-4-Mini-Hindi-4B-Instruct
A small Hindi-focused chat model from NVIDIA, tuned for Indian-context answersSmall · Open weights · 2024
🇺🇸 United StatesApple Foundation Models
Apple's on-device and server language models behind Apple IntelligenceGeneral · API only · 2024
🇺🇸 United StatesGemma
Small open-weight language models from Google, in 2B and 7B sizesGeneral · Conditional licence · 2024
🇺🇸 United StatesGemma 3n
Mobile-first open model family for on-device text, image and audio workMultimodal · Open weights · 2025
🇺🇸 United StatesPhi-1
A small Microsoft model specialised for basic Python codingCode · Open weights · 2023
🇺🇸 United StatesPhi-4-mini
A 3.8B-parameter compact language model from Microsoft for reasoning, maths and codeSmall · Open weights · 2025
🇨🇳 ChinaChatGLM-6B
Open bilingual dialogue model with 6.2 billion parametersAssistant · Open weights
WorldOpenCoder
Open code model family with full training data and pipelineCode · Open weights · 2024
WorldTinyLlama
A compact 1.1 billion parameter open language model.Small · Open weights · 2023
🇬🇧 United KingdomStableLM 2
A small open-weight language model by Stability AIGeneral · Open weights · 2024
🇺🇸 United StatesSmolLM2
Compact language models for on-device useGeneral · Open weights · 2025
🇩🇪 GermanyPharia-1-LLM-7B
Multilingual 7B parameter decoder model by Aleph Alpha ResearchGeneral · Open weights
🇨🇳 ChinaMiniCPM
Efficient small language models for end-side devicesGeneral · Open weights · 2024
🇮🇳 IndiaSarvam-1
A 2-billion parameter language model for Indian languages.Regional · Conditional licence · 2024
🇮🇳 IndiaSarvam 2B
Small language model for English and ten Indian languages.Small · Open weights · 2024
🇺🇸 United StatesOpenELM
Apple's small open language models with a full training and inference releaseSmall · Open weights · 2024
🇮🇳 IndiaPragna-1B
Small decoder model for Hindi, Bangla, Gujarati and EnglishSmall · Open weights
🇫🇷 FranceMinistral 3B and 8B
Two small Mistral AI models built for on-device and edge computing.Small · API only · 2024