Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
Mage-VL-Cowork
Modelsimage text to text model by microsoft · transformers
microsoft/Mage-VL-Cowork -
Ternary-Bonsai-2-2B-gguf
Modelsimage text to text model by prism-ml · llama.cpp
prism-ml/Ternary-Bonsai-2-2B-gguf -
Lara-4-Mini-Base
Modelstext generation model by translated · transformers
translated/Lara-4-Mini-Base -
Ternary-Bonsai-2-4B-gguf
Modelsimage text to text model by prism-ml · llama.cpp
prism-ml/Ternary-Bonsai-2-4B-gguf -
image text to text model by Sakura721 · gguf
Sakura721/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-GGUF -
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 -
inclusionAI: Ling 3.1 Flash
ModelsLing 3.1 Flash is a hybrid reasoning mixture-of-experts model from inclusionAI, with 25B active parameters out of 560B total.
inclusionai/ling-3.1-flash -
NVIDIA: Nemotron 3 Ultra
ModelsNVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...
nvidia/nemotron-3-ultra-550b-a55b -
NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...
nvidia/nemotron-3-ultra-550b-a55b:free -
Nous: Hermes 4 405B
ModelsHermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B and released by Nous Research. It introduces a hybrid reasoning mode, where the model can choose to deliberate internally with...
nousresearch/hermes-4-405b -
MiniMax: MiniMax M1
ModelsMiniMax-M1 is a large-scale, open-weight reasoning model designed for extended context and high-efficiency inference. It leverages a hybrid Mixture-of-Experts (MoE) architecture paired with a custom "lightning attention" mechanism, allowing it...
minimax/minimax-m1 -
DeepSeek: DeepSeek V3.1
ModelsDeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...
deepseek/deepseek-chat-v3.1 -
Qwen: Qwen3.6 27B
ModelsQwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026. It features hybrid multimodal capabilities — accepting text, image, and video inputs...
qwen/qwen3.6-27b -
KT: Mi:dm K 3.0 Pro
ModelsMi:dm K 3.0 Pro is a Mixture-of-Experts reasoning model from KT, with 120B total and 12B active parameters. It uses a hybrid architecture that mixes Mamba, MoE and attention layers.
kt/midm-k-3.0-pro -
Ling 3.2 Flash is a hybrid reasoning model from inclusionAI that accepts text and image input, with a 1M-token context window and up to 200 images per request. Thinking can...
inclusionai/ling-3.2-flash:free -
Qwen: Qwen3.5-Flash
ModelsThe Qwen3.5 native vision-language Flash models are built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. Compared to the...
qwen/qwen3.5-flash-02-23 -
Qwen: Qwen3.6 Plus
ModelsQwen 3.6 Plus builds on a hybrid architecture that combines efficient linear attention with sparse mixture-of-experts routing, enabling strong scalability and high-performance inference. Compared to the 3.5 series, it delivers...
qwen/qwen3.6-plus -
Qwen: Qwen3.5-35B-A3B
ModelsThe Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, achieving higher inference efficiency. Its overall...
qwen/qwen3.5-35b-a3b -
Qwen: Qwen3.5-122B-A10B
ModelsThe Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. In terms of...
qwen/qwen3.5-122b-a10b -
Qwen: Qwen3.5 397B A17B
ModelsThe Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. It delivers...
qwen/qwen3.5-397b-a17b -
Qwen: Qwen3.6 35B A3B
ModelsQwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It uses a hybrid sparse mixture-of-experts architecture combining Gated...
qwen/qwen3.6-35b-a3b -
The Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency. In a variety of...
qwen/qwen3.5-plus-02-15 -
Xiaomi: MiMo-V2.6-Flash
ModelsMiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi. Built on a Mixture-of-Experts architecture with 309B total parameters and 15B activated per token, it employs a hybrid attention mechanism for...
xiaomi/mimo-v2.6-flash -
Z.ai: GLM 5.3 Flash
ModelsGLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while...
z-ai/glm-5.3-flash
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.