Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
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: Qwen3.5-35B-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 -
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 -
Z.ai: GLM 4.5V
ModelsGLM-4.5V is a vision-language foundation model for multimodal agent applications. Built on a Mixture-of-Experts (MoE) architecture with 106B parameters and 12B activated parameters, it achieves state-of-the-art results in video understanding,...
z-ai/glm-4.5v -
Inception: Mercury 2
ModelsMercury 2 is an extremely fast reasoning LLM, and the first reasoning diffusion LLM (dLLM). Instead of generating tokens sequentially, Mercury 2 produces and refines multiple tokens in parallel, achieving...
inception/mercury-2 -
Unlimited-OCR
Modelsimage text to text model by baidu · transformers
baidu/Unlimited-OCR -
Llama-3.1-8B-Omni
Modelsmodel by ICTNLP · llama-omni
ICTNLP/Llama-3.1-8B-Omni -
Inception: Mercury 2.5
ModelsMercury 2.5 is the fastest reasoning LLM, and the latest diffusion LLM (dLLM) from Inception. Instead of generating tokens sequentially, Mercury 2.5 produces and refines multiple tokens in parallel, achieving...
inception/mercury-2.5 -
ZDTaichu5.0-9B
Modelsimage text to text model by TaichuAI
TaichuAI/ZDTaichu5.0-9B -
DeepSeek-OCR
Modelsimage text to text model by deepseek-ai · transformers
deepseek-ai/DeepSeek-OCR -
neutts-air
Modelstext to speech model by neuphonic
neuphonic/neutts-air -
GOT-OCR2_0
Modelsimage text to text model by stepfun-ai
stepfun-ai/GOT-OCR2_0 -
bitnet-b1.58-2B-4T
Modelstext generation model by microsoft · transformers
microsoft/bitnet-b1.58-2B-4T -
text classification model by papluca · transformers
papluca/xlm-roberta-base-language-detection -
smolvla_base
Modelsrobotics model by lerobot · lerobot
lerobot/smolvla_base -
Octopus-v2
Modelstext generation model by NexaAI · transformers
NexaAI/Octopus-v2 -
Qianfan-OCR
Modelsimage text to text model by baidu · transformers
baidu/Qianfan-OCR -
automatic speech recognition model by nvidia · nemo
nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B -
Anthropic: Claude Opus 4.1
ModelsClaude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified and shows notable gains...
anthropic/claude-opus-4.1 -
DiffuCoder-7B-cpGRPO
Modelsmodel by apple
apple/DiffuCoder-7B-cpGRPO -
DeepSeek-OCR-2
Modelsimage text to text model by deepseek-ai · transformers
deepseek-ai/DeepSeek-OCR-2 -
Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified and shows notable gains...
anthropic/claude-opus-4.1:batch
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.