Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
flux_text_encoders
Modelsmodel by comfyanonymous
comfyanonymous/flux_text_encoders -
t5-v1_1-xxl-encoder-gguf
Modelsmodel by city96 · gguf
city96/t5-v1_1-xxl-encoder-gguf -
model by pottokao
pottokao/Qwen-Image-2.1-Text-Encoder-Heretic-GGUF -
text to image model by ponpoke
ponpoke/flux2-klein-9b-uncensored-text-encoder -
openjev
Modelstext classification model by AlexWortega · transformers
AlexWortega/openjev -
vit-gpt2-image-captioning
Modelsimage to text model by nlpconnect · transformers
nlpconnect/vit-gpt2-image-captioning -
needle
Modelsmodel by Cactus-Compute · jax
Cactus-Compute/needle -
meta-encoder-v1
Modelsfeature extraction model by facebook · transformers
facebook/meta-encoder-v1 -
trocr-base-handwritten
Modelsimage to text model by microsoft · transformers
microsoft/trocr-base-handwritten -
model by Momoking · comfyui
Momoking/Qwen3-VL-32B-Heretic-MiniMax-H3-NVFP4 -
text to image model by AtomicChat · gguf
AtomicChat/Qwen-Image-2.1-Turbo-Uncensored-GGUF -
text ranking model by jinaai · transformers
jinaai/jina-reranker-v2-base-multilingual -
ms-marco-MiniLM-L6-v2
Modelstext ranking model by cross-encoder · sentence-transformers
cross-encoder/ms-marco-MiniLM-L6-v2 -
Dolphin
Modelsimage text to text model by ByteDance · transformers
ByteDance/Dolphin -
UltraBERT-380M
Modelsfill mask model by dmis-lab · transformers
dmis-lab/UltraBERT-380M -
UltraBERT-150M
Modelsfill mask model by dmis-lab · transformers
dmis-lab/UltraBERT-150M -
Nemotron-3.5-Rerank-8B-BF16
Modelstext ranking model by nvidia · sentence-transformers
nvidia/Nemotron-3.5-Rerank-8B-BF16 -
vela3-fast
Modelszero shot classification model by vllm-sr · transformers
vllm-sr/vela3-fast -
DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...
deepseek/deepseek-v4.1-flash -
DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...
deepseek/deepseek-v4.1-flash:batch -
StepFun: Step 3.7 Flash
ModelsStep 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating roughly 11B parameters...
stepfun/step-3.7-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.