Search Results for "small"
Sort By:
30 projects for "small" with 2 filters applied:
-
Paessler: Easy to Use With Enterprise Power. Free TrialYou shouldn't have to choose between a monitoring tool that's easy to use and one that's powerful enough for a complex environment. PRTG's low-code interface lets any admin build dashboards, set alerts and monitor devices without scripting, while custom sensors and full API access are there when your team needs deeper control. One platform, no compromise. Download a free 30-day trial now.
-
$300 Free Credits to Build on Google CloudPut your $300 in credit toward real workloads, then keep building with free monthly usage for 20+ products. No commitment and no charge until you upgrade.
-
1
SAM 3D Objects
Models for object and human mesh reconstruction
...Given one RGB image and object masks (for example, from the Segment Anything family), it can generate a textured 3D mesh for each object, including pose and approximate scene layout. The model is specifically designed to be robust in real-world images with clutter, occlusions, small objects, and unusual viewpoints, where many earlier 3D-from-image systems struggle. It supports both single-object and multi-object generation, allowing you to reconstruct entire scenes rather than just isolated items. The repository provides code to run inference, a quickstart demo.py script, and environment setup instructions that connect to hosted checkpoints and configuration files. ... -
2
MiniCPM5-2B
SOTA on-device LLMs, small yet powerful
MiniCPM5-2B is a family of compact language models developed for local, on-device, and resource-constrained AI workloads. The current MiniCPM5 series includes dense 1B and 2B models designed to deliver strong capability with a small deployment footprint. MiniCPM5-2B provides a 131K-token context window and targets assistants, coding agents, reasoning, tool use, and other agentic tasks. The repository includes base, supervised fine-tuned, and deployment-ready model variants. Quantized releases are available in formats such as GGUF, MLX, GPTQ, and DSpark. It also provides fine-tuning, quantization, deployment, and agent-skill resources for adapting models to different environments. ... -
3
Cactus Needle
26m function call model that runs on incredibly small devices
Needle is an experimental 26-million-parameter function-calling model designed to run on extremely small devices such as phones, watches, glasses, and low-power personal AI hardware. It is based on a Simple Attention Network architecture and was distilled from a much larger model to focus on fast, compact tool-use behavior. The project provides open weights, training details, dataset generation resources, and a playground for testing the model with custom tools. -
4
MiniMind-O
A 0.1B Omni model trained from scratch
MiniMind-O is an educational open-source project for building a small end-to-end Omni model from scratch. It extends the MiniMind family by exploring a model that can handle text, audio, and image inputs while producing text and streaming speech outputs. The project is designed to make multimodal AI training more accessible by keeping the model size small enough for ordinary personal hardware. It includes both mini and full training data paths, allowing learners to run a complete workflow quickly or reproduce the released model setup more closely. ... -
Build Agents and Models on One PlatformGemini Enterprise Agent Platform is Google Cloud's comprehensive platform for developers to build, scale, govern, and optimize agents and models. Choose from Google's most advanced models and third-party models like Anthropic's Claude Model Family.
-
5
FastVLM
This repository contains the official implementation of FastVLM
...Instead of elaborate pruning stages, the design trades off resolution and token count through input scaling, simplifying the pipeline while maintaining strong accuracy. Reported results highlight dramatic speedups in time-to-first-token and competitive quality versus contemporary open VLMs, including comparisons across small and larger variants. The repository documents model variants, showcases head-to-head numbers against known baselines, and explains how the encoder integrates with common LLM backbones. Apple’s research brief frames FastVLM as targeting real-time or latency-sensitive scenarios, where lowering visual token pressure is critical to interactive UX. ... -
6
SemIf
Semantic ifs from open models, on a 3090 at home
SemIf, formerly OpenJev, is an independent research project for making small semantic decisions with open language models. Instead of generating text and parsing it afterward, it reads probabilities directly from declared answer options. Each request supplies state, a runtime-defined question, and typed choices, allowing the model to behave like a semantic conditional. Shared-state execution can reuse a long context across many related decisions to reduce repeated computation. ... -
7
MiniCPM5
MiniCPM5: SOTA on-device LLMs, small yet powerful
MiniCPM is an open-source family of compact large language models developed by OpenBMB for efficient AI inference on personal devices and resource-constrained hardware. Its latest MiniCPM5 series includes 1B and 2B-class models optimized for local deployment. The models support text generation, coding, mathematical reasoning, and autonomous agent workflows. MiniCPM5-2B uses a Transformer architecture with grouped-query attention and a 131,072-token context window. Earlier releases explore... -
8
Large Concept Model
Language modeling in a sentence representation space
Large Concept Model is a research codebase centered on concept-centric representation learning at scale, aiming to capture shared structure across many categories and modalities. It organizes training around concepts (rather than just raw labels), encouraging models to understand attributes, relations, and compositional structure that transfer across tasks. The repository provides training loops, data tooling, and evaluation routines to learn and probe these concept embeddings, typically... -
9
VibeThinker
Diversity-driven optimization and large-model reasoning ability
VibeThinker is a compact but high-capability open-source language model released by WeiboAI (Sina AI Lab). It contains about 1.5 billion parameters, far smaller than many “frontier” models, yet it is explicitly optimized for reasoning, mathematics, and code generation tasks rather than general open-domain chat. The innovation lies in its training methodology: the team uses what they call the Spectrum-to-Signal Principle (SSP), where a first stage emphasizes diversity of reasoning paths (the... -
Our Free Plans just got better! | Auth0You asked, we delivered! Auth0 is excited to expand our Free and Paid plans to include more options so you can focus on building, deploying, and scaling applications without having to worry about your security. Auth0 now, thank yourself later.
-
10
MediaPipe Face Detection
Detect faces in an image
The MediaPipe Face Detection model is a high-performance, real-time face detection solution that uses machine learning to identify faces in images and video streams. It is optimized for mobile and embedded platforms, offering fast and accurate face detection while maintaining a small memory footprint. This model supports multiple face detections and is highly efficient, making it suitable for a variety of applications such as augmented reality, user authentication, and facial expression analysis. -
11
DeiT (Data-efficient Image Transformers)
Official DeiT repository
...Its key idea is a specialized distillation strategy—including a learnable “distillation token”—that lets a transformer learn effectively from a CNN or transformer teacher on modest-scale datasets. The project provides compact ViT variants (Tiny/Small/Base) that achieve excellent accuracy–throughput trade-offs, making transformers practical beyond massive pretraining regimes. Training involves carefully tuned augmentations, regularization, and optimization schedules to stabilize learning and improve sample efficiency. The repo offers pretrained checkpoints, reference scripts, and ablation studies that clarify which ingredients matter most for data-efficient ViT training. -
12
OpenAI Quickstart Python
Python example app from the OpenAI API quickstart tutorial
...It provides practical, beginner-friendly examples to help developers quickly learn how to send requests, handle responses, and build basic applications using the OpenAI Python SDK. The examples folder includes small, self-contained projects showcasing common use cases like chat completions, tool usage, and interactive interfaces. Each example is designed to be easily runnable with minimal setup—requiring only Python, a virtual environment, and an API key. The repository also includes environment setup guides and example scripts, such as a simple Flask web app for chat interactions, allowing developers to test OpenAI API integrations locally. ... -
13
Mask2Former
Code release for "Masked-attention Mask Transformer
...A pixel decoder fuses multi-scale features and feeds masked attention in the transformer so each query focuses computation on its current spatial support. This leads to accurate masks with sharp boundaries and strong small-object performance while remaining efficient on high-resolution inputs. The project provides extensive configurations and pretrained models across popular benchmarks like COCO, ADE20K, and Cityscapes. Built on top of Detectron2, it includes training scripts, inference tools, and visualization utilities that make experimentation straightforward. -
14
PyTorch-BigGraph
Generate embeddings from large-scale graph-structured data
PyTorch-BigGraph (PBG) is a system for learning embeddings on massive graphs—think billions of nodes and edges—using partitioning and distributed training to keep memory and compute tractable. It shards entities into partitions and buckets edges so that each training pass only touches a small slice of parameters, which drastically reduces peak RAM and enables horizontal scaling across machines. PBG supports multi-relation graphs (knowledge graphs) with relation-specific scoring functions, negative sampling strategies, and typed entities, making it suitable for link prediction and retrieval. Its training loop is built for throughput: asynchronous I/O, memory-mapped tensors, and lock-free updates keep GPUs and CPUs fed even at extreme scale. ... -
15
Mistral Small 4
Model that fuses instruct, reasoning and agentic skills
The Mistral Small 4 collection is a set of open-weight large language models developed by Mistral AI that aim to unify multiple capabilities, including instruction following, reasoning, and coding, within a single efficient architecture. These models are part of the broader Mistral Small family, which is designed to deliver strong performance across a wide range of everyday AI tasks while maintaining relatively low latency and efficient deployment requirements. -
16
Inkling-Small
Efficient multimodal MoE model for coding, tools, and reasoning
...Its 42-layer decoder routes each token through six of 256 specialized experts plus two shared experts, while hybrid local and global attention supports efficient processing. Inkling-Small performs strongly across software engineering, tool use, mathematics, vision, and audio benchmarks, including 80.2% on SWE-Bench Verified and 95.5% on AIME 2026. -
17
t5-small
T5-Small: Lightweight text-to-text transformer for NLP tasks
T5-Small is compatible with major deep learning frameworks including PyTorch, TensorFlow, JAX, and ONNX. The model is open-source under the Apache 2.0 license and has wide support across Hugging Face's ecosystem. -
18
Devstral Small 2
Lightweight 24B agentic coding model with vision and long context
...It introduces vision capabilities, enabling image understanding alongside text for more versatile development workflows. Devstral Small 2 supports a 256k context window, allowing it to reason across large repositories, long diffs, and extended technical contexts. Its architecture improves generalization across diverse prompts and coding environments while leveraging advanced attention scaling techniques. -
19
Nemotron 3
Large language model developed and released by NVIDIA
...It is the post-trained and FP8-quantized variant of the Nemotron 3 Nano model, meaning its weights and activations are represented in 8-bit floating point (FP8) to dramatically reduce memory usage and computational cost while retaining high accuracy. The base Nano architecture uses a hybrid Mamba-Transformer Mixture-of-Experts (MoE) design, allowing the model to activate only a small fraction of its 31.6 billion parameters per token, which improves speed and efficiency without sacrificing quality on complex queries. This configuration supports a massive context length of up to 1 million tokens, making it suitable for long-context reasoning, agentic tasks, extended dialogues, and applications like code generation or document summarization. -
20
bge-small-en-v1.5
Compact English sentence embedding model for semantic search tasks
BAAI/bge-small-en-v1.5 is a lightweight English sentence embedding model developed by the Beijing Academy of Artificial Intelligence (BAAI) as part of the BGE (BAAI General Embedding) series. Designed for dense retrieval, semantic search, and similarity tasks, it produces 384-dimensional embeddings that can be used to compare and rank sentences or passages. -
21
Ministral 3 3B Base 2512
Small 3B-base multimodal model ideal for custom AI on edge hardware
...It supports dozens of languages, making it practical for multilingual, global, or distributed environments. With a large 256k token context window, it can handle long documents, extended inputs, or multi-step processing workflows even at its small size. -
22
Ministral 3 3B Instruct 2512
Ultra-efficient 3B multimodal instruct model built for edge deployment
...As an FP8 instruct-fine-tuned model, it is optimized for chat, instruction following, and compact agentic tasks while maintaining strong adherence to system prompts. Despite its small size, it delivers efficient real-time performance and can run locally on a single 8GB GPU, with further memory reductions through quantization. It supports dozens of languages across major global regions, making it well-suited for multilingual and embedded applications. The model also provides function calling, clean JSON output, and stable tool-use behavior, enabling it to serve as a small but effective agentic system. -
23
Hy3
Open code agent for Lean 4 proofs and formal software verification
Leanstral 1.5 119B A6B is an open-source code agent model from Mistral AI designed specifically for Lean 4, a proof assistant used to express and verify complex mathematical objects and formal software specifications. Built as part of the Mistral Small 4 family, it combines multimodal capabilities with an efficient Mixture-of-Experts architecture containing 119B total parameters and 6.5B activated per token. The model uses 128 experts with four active for each token and supports a 256K-token context window, making it suitable for extended formal reasoning and large verification tasks. ... -
24
Leanstral 1.5
Open code agent for Lean 4 proofs and formal software verification
Leanstral 1.5 119B A6B is an open-source code agent model from Mistral AI designed specifically for Lean 4, a proof assistant used to express and verify complex mathematical objects and formal software specifications. Built as part of the Mistral Small 4 family, it combines multimodal capabilities with an efficient Mixture-of-Experts architecture containing 119B total parameters and 6.5B activated per token. The model uses 128 experts with four active for each token and supports a 256K-token context window, making it suitable for extended formal reasoning and large verification tasks. ... -
25
DeepSeek-V3.1-Terminus
685B model with improved agents and consistency
...The update also refines agentic capabilities, especially for the Code Agent and Search Agent, leading to better tool integration and query handling. Benchmarks show small but notable gains, such as raising MMLU-Pro from 84.8 to 85.0, GPQA-Diamond from 80.1 to 80.7, and SWE Verified from 66.0 to 68.4, along with significant improvements in agent benchmarks like BrowseComp (30.0 → 38.5) and Terminal-bench (31.3 → 36.7). The model structure remains the same as DeepSeek-V3, ensuring compatibility with existing deployment methods, with updated inference demos provided for community use.
