Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
Confucius4-R2T2
Modelsautomatic speech recognition model by netease-youdao · transformers
netease-youdao/Confucius4-R2T2 -
Underdog-Bark-3.0
Modelsautomatic speech recognition model by ConwayResearch · transformers
ConwayResearch/Underdog-Bark-3.0 -
Earlybird-29M
Modelsautomatic speech recognition model by sahilmahendrakar · transformers
sahilmahendrakar/Earlybird-29M -
FLUX-3-Image-Klein_GGUFs
Modelstext to image model by realrebelai
realrebelai/FLUX-3-Image-Klein_GGUFs -
Underdog-Bark-3.0-Clean
Modelsautomatic speech recognition model by ConwayResearch · transformers
ConwayResearch/Underdog-Bark-3.0-Clean -
MOSS-Image_GGUFs
Modelstext to image model by realrebelai
realrebelai/MOSS-Image_GGUFs -
Phonon-2.5
Modelsautomatic speech recognition model by FermionResearch · mlx
FermionResearch/Phonon-2.5 -
Phonon-2.5-English
Modelsautomatic speech recognition model by FermionResearch · mlx
FermionResearch/Phonon-2.5-English -
voxlock
Modelsaudio to audio model by arbazsiddiqui
arbazsiddiqui/voxlock -
Amazon: Nova Micro 1.0
ModelsAmazon Nova Micro 1.0 is a text-only model that delivers the lowest latency responses in the Amazon Nova family of models at a very low cost. With a context length...
amazon/nova-micro-v1 -
Gemini 3.8 Live
ModelsLow-latency voice agents for real-time conversations.
-
GPT-6.1 Sol
ModelsComplex coding and professional work, at a lower cost than GPT-6 Astra.
-
Claude Haiku 4.5
ModelsThe fastest Claude model: high-volume replies and routing at a low running cost.
-
Gemini 4 Argon
ModelsReasoning with quicker answers and lower running cost than Carbon, for everyday agents and analysis.
-
Claude Haiku 5.5
ModelsQuick, low-cost replies for busy, repetitive work: summarising, sorting requests and live customer chat.
-
Gemini 4 Hydrogen
ModelsFast, low-cost help for everyday coding and agent workflows, with room for very long documents.
-
Tencent: Hy3 preview
ModelsHy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic workflows and production use. It supports configurable reasoning levels across disabled, low, and high modes, allowing it to...
tencent/hy3-preview -
Mistral: Mistral Small 3
ModelsMistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed...
mistralai/mistral-small-24b-instruct-2501 -
Amazon: Nova Lite 1.0
ModelsAmazon Nova Lite 1.0 is a very low-cost multimodal model from Amazon that focused on fast processing of image, video, and text inputs to generate text output. Amazon Nova Lite...
amazon/nova-lite-v1 -
IBM: Granite 4.2 8B
ModelsGranite 4.2 8B is a dense reasoning model from IBM. It is suited for mathematics, code generation, multilingual dialogue, and agentic workflows that need multi-step reasoning. It supports full, low-effort,...
ibm-granite/granite-4.2-8b -
AionLabs: Aion 3.5 Mini
ModelsAion 3.5 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It is the smaller, lower-cost sibling of Aion 3.5 and uses...
aion-labs/aion-3.5-mini -
Anthropic: Claude Sonnet 5
ModelsSonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max,...
anthropic/claude-sonnet-5 -
Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max,...
anthropic/claude-sonnet-5:batch -
SpaceXAI: Grok 4.20
ModelsGrok 4.20 is a reasoning model from SpaceXAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering...
x-ai/grok-4.20
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.