Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
Ollama
ModelsRuns open models such as gpt-oss, Qwen and DeepSeek on your own computer.
curl -fsSL https://ollama.com/install.sh | sh -
needle3
Modelstext generation model by Cactus-Compute · cactus-compute
Cactus-Compute/needle3 -
whistle
Modelsautomatic speech recognition model by Cactus-Compute · cactus-compute
Cactus-Compute/whistle -
VisionHOPE
Modelsimage classification model by PSRben
PSRben/VisionHOPE -
mirage
Modelsimage text to text model by Cactus-Compute · cactus-compute
Cactus-Compute/mirage -
cactus
Modelstext generation model by Cactus-Compute · cactus-compute
Cactus-Compute/cactus -
needle
Modelsmodel by Cactus-Compute · jax
Cactus-Compute/needle -
hobbylm-1B-computer-use
Modelstext generation model by Hobbylm · peft
Hobbylm/hobbylm-1B-computer-use -
needle2
Modelstext generation model by Cactus-Compute · cactus-needle
Cactus-Compute/needle2 -
Holo3-35B-A3B
Modelsimage text to text model by Hcompany · transformers
Hcompany/Holo3-35B-A3B -
Qwenx86-4B-compact
Modelsmodel by Quazim0t0
Quazim0t0/Qwenx86-4B-compact -
openjev
Modelszero shot classification model by openjev
openjev/openjev -
ALoDLM-8B
Modelstext generation model by amazon
amazon/ALoDLM-8B -
Mage-VL-Cowork
Modelsimage text to text model by microsoft · transformers
microsoft/Mage-VL-Cowork -
NorthCUA-Pro
Modelsimage text to text model by beipo-ai · transformers
beipo-ai/NorthCUA-Pro -
nemotron-3.5-120b-cq
Modelsimage text to text model by Cactus-Compute · mlx
Cactus-Compute/nemotron-3.5-120b-cq -
GPT-6 Astra
ModelsThe most demanding work: complex reasoning, research, computer use and document creation.
-
NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully...
nvidia/nemotron-3-nano-30b-a3b -
NVIDIA: Nemotron 3 Super
ModelsNVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...
nvidia/nemotron-3-super-120b-a12b -
DeepSeek: DeepSeek V3.2
ModelsDeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...
deepseek/deepseek-v3.2 -
OpenAI: o3 Pro
ModelsThe o-series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o3-pro model uses more compute to think harder and provide consistently...
openai/o3-pro -
Qwen: Qwen3.7 Flash
ModelsQwen3.7 Flash is a vision-language reasoning model from Alibaba. It is suited for multimodal agents, visual coding, search, and computer interaction, with strengths in object recognition, spatial understanding, and real-world...
qwen/qwen3.7-flash -
Anthropic: Claude Opus 4.5
ModelsClaude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and...
anthropic/claude-opus-4.5 -
Anthropic: Claude Haiku 5.5
ModelsClaude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. It succeeds Claude Haiku 4.5 with stronger coding, computer use, and...
anthropic/claude-haiku-5.5
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.