#

Small-Model

AI tools tagged Small-Model.

32 tools · handpicked & curated
// price
BTLM-3B Cerebras' compact open-weight model tuned to punch above its parameter count
Command R7B Cohere's smallest current-generation Command model
DistilBERT Hugging Face's distilled, 40%-smaller version of BERT that retains most of its performance
Falcon 3 TII's efficient small-model open-weight family
Falcon 7B TII's compact Falcon tier that helped popularize the original Falcon release
Gemini Nano Google's on-device Gemini tier built into Pixel and Android
Gemma 3 Google's open-weight model family built from Gemini research
GPT-OSS-20B The smaller, single-GPU-friendly tier of OpenAI's open-weight model release
Llama 3.1 8B Meta's compact tier of the Llama 3.1 generation
MiniCPM OpenBMB's efficient small model designed to run well on phones and edge devices
MiniCPM-V OpenBMB's multimodal edge model, capable of GPT-4V-level vision tasks on a phone
Ministral 8B Mistral's compact model built for on-device and edge deployment
Mistral 7B Mistral's original compact open-weight model that outperformed larger rivals
Mistral Small 3 Mistral's efficient small model tier for latency-sensitive workloads
Nemotron Nano NVIDIA's small, efficient Nemotron tier optimised for edge deployment
Nemotron-3 8B NVIDIA's earlier compact enterprise-focused Nemotron model
Orca-Math Microsoft's small model specialised in grade-school math word problems
Phi-2 Microsoft's earlier 2.7B model demonstrating outsized small-model performance
Phi-3 Microsoft's compact open-weight model family for on-device use
Phi-3-medium The 14B-parameter tier of Microsoft's Phi-3 family, tuned for stronger reasoning
Phi-3-small The 7B-parameter tier of Microsoft's Phi-3 small-language-model family
Phi-3-vision Multimodal member of the Phi-3 family for image reasoning on-device
Phi-3.5-mini Microsoft's updated compact model in the Phi-3 line
Phi-4 Microsoft's small reasoning-focused model that punches above its parameter count
Phi-4-reasoning Reasoning-tuned variant of Phi-4 trained with chain-of-thought supervision
Reka Edge Reka's smallest, on-device-friendly model tier
SantaCoder BigCode's small multilingual code model preceding StarCoder
SmolLM Hugging Face's original family of small, fully open language models
SmolLM2 Hugging Face's fully open small-model family for on-device use
StableLM 2 Stability AI's open-weight small language model
StableLM 3B Stability AI's early compact open-weight language model, preceding StableLM 2
StableLM Zephyr Stability AI's chat-tuned small model built on StableLM 3B