Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
zephyr-7b-alpha
Modelstext generation model by HuggingFaceH4 · transformers
HuggingFaceH4/zephyr-7b-alpha -
zephyr-7b-beta
Modelstext generation model by HuggingFaceH4 · transformers
HuggingFaceH4/zephyr-7b-beta -
Hugging Face Hub
ModelsThe main public hub for open models, datasets and demo apps (Spaces).
-
pi0_old
Modelsrobotics model by lerobot · lerobot
lerobot/pi0_old -
GR00T-N1-2B
Modelsrobotics model by nvidia
nvidia/GR00T-N1-2B -
smolvla_base
Modelsrobotics model by lerobot · lerobot
lerobot/smolvla_base -
Magma-8B
Modelsrobotics model by microsoft · transformers
microsoft/Magma-8B -
Alpamayo-R1-10B
Modelsrobotics model by nvidia · transformers
nvidia/Alpamayo-R1-10B -
Whisper
ModelsOpenAI's open speech-to-text model.
pip install -U openai-whisper -
MotionBricks
Modelsrobotics model by nvidia · pytorch
nvidia/MotionBricks -
Alpamayo2-Edge
Modelsrobotics model by nvidia
nvidia/Alpamayo2-Edge -
robo-diffusion
Modelstext to image model by nousr · diffusers
nousr/robo-diffusion -
Step3-VL-10B
Modelsimage text to text model by stepfun-ai
stepfun-ai/Step3-VL-10B -
AIRoA-0
Modelsrobotics model by airoa-org · openpi
airoa-org/AIRoA-0 -
s2-pro
Modelstext to speech model by fishaudio
fishaudio/s2-pro -
AuK
Modelstext to speech model by tencent
tencent/AuK -
audio.cpp-gguf
Modelstext to speech model by audio-cpp · audio.cpp
audio-cpp/audio.cpp-gguf -
NVIDIA: Switchyard
ModelsSwitchyard is an open-source model routing system that switches between multiple models to optimize the cost of requests. By default it will use OpenRouter market data to select the most...
nvidia/switchyard -
Perplexity: Sonar
ModelsSonar is lightweight, affordable, fast, and simple to use — now featuring citations and the ability to customize sources. It is designed for companies seeking to integrate lightweight question-and-answer features...
perplexity/sonar -
ScaleDown: Summarize
ModelsSummarize is an abstractive summarization model from ScaleDown. It condenses long text and documents into a fluent, faithful rewrite rather than lifting sentences from the source, and is suited for...
scaledown/summarize -
Relace: Relace Apply 3
ModelsRelace Apply 3 is a specialized code-patching LLM that merges AI-suggested edits straight into your source files. It can apply updates from GPT-4o, Claude, and others into your files at...
relace/relace-apply-3 -
Sonar Deep Research is a research-focused model designed for multi-step retrieval, synthesis, and reasoning across complex topics. It autonomously searches, reads, and evaluates sources, refining its approach as it gathers...
perplexity/sonar-deep-research -
StepFun: Step 3.5 Flash
ModelsStep 3.5 Flash is StepFun's most capable open-source foundation model. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parameters per token....
stepfun/step-3.5-flash -
DeepSeek: R1 0528
ModelsMay 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active...
deepseek/deepseek-r1-0528
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.