SSyncDev

The SyncDev models directory

AI Models Directory

Find the right model for the work you need to do. Explore 3,712 profiles, from hosted language models to image, audio and video generators and downloadable checkpoints.

Explore all models · Page 54

Start with our shortlist, search a model family, or filter by task and deployment. Prices apply to the listed route; a dash means a figure is not recorded.

pyannote/voice-activity-detection
pyannote
5.0————
pysentimiento/robertuito-sentiment-analysis
pysentimiento
5.0————
Qdrant/all-MiniLM-L6-v2-onnx
Qdrant
5.0————
Qdrant/bge-small-en-v1.5-onnx-Q
Qdrant
5.0————
Qdrant/bm25
Qdrant
5.0————
qilowoq/bge-reranker-v2-m3-en-ru
qilowoq
5.0————
QuantFactory/TableLLM-13b-GGUF
QuantFactory
5.0————
QuantStack/Wan2.1_14B_VACE-GGUF
QuantStack
5.0————
QuantStack/Wan2.2-Fun-A14B-Control-GGUF
QuantStack
5.0————
QuantStack/Wan2.2-S2V-14B-GGUF
QuantStack
5.0————
QuantStack/Wan2.2-T2V-A14B-GGUF
QuantStack
5.0————
QuantStack/Wan2.2-TI2V-5B-GGUF
QuantStack
5.0————
QuantTrio/Qwen3.5-9B-AWQ
QuantTrio
5.0————
Qwen/Qwen2-Audio-7B
Qwen
5.0————
Qwen/Qwen2-Audio-7B-Instruct
Qwen
5.0————
Qwen/Qwen2-VL-2B-Instruct
Qwen
5.0————
Qwen/Qwen2-VL-7B-Instruct
Qwen
5.0————
Qwen/Qwen2-VL-7B-Instruct-AWQ
Qwen
5.0————
Qwen/Qwen2.5-Math-PRM-7B
Qwen
5.0————
Qwen/Qwen2.5-VL-32B-Instruct-AWQ
Qwen
5.0————
Qwen/Qwen2.5-VL-3B-Instruct
Qwen
5.0————
Qwen/Qwen2.5-VL-7B-Instruct-AWQ
Qwen
5.0————
Qwen/Qwen3-ASR-0.6B
Qwen
5.0————
Qwen/Qwen3-ASR-1.7B
Qwen
5.0————
Qwen/Qwen3-Reranker-0.6B
Qwen
5.0————
Qwen/Qwen3-TTS-12Hz-0.6B-Base
Qwen
5.0————
Qwen/Qwen3-TTS-12Hz-0.6B-CustomVoice
Qwen
5.0————
Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice
Qwen
5.0————
Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign
Qwen
5.0————
Qwen/Qwen3-VL-2B-Instruct
Qwen
5.0————
Qwen/Qwen3-VL-32B-Instruct
Qwen
5.0————
Qwen/Qwen3-VL-4B-Instruct
Qwen
5.0————
Qwen/Qwen3-VL-8B-Instruct
Qwen
5.0————
Qwen/Qwen3-VL-8B-Instruct-FP8
Qwen
5.0————
Qwen/Qwen3-VL-Embedding-2B
Qwen
5.0————
Qwen/Qwen3-VL-Embedding-8B
Qwen
5.0————
Qwen/Qwen3-VL-Reranker-2B
Qwen
5.0————
Qwen/Qwen3-VL-Reranker-8B
Qwen
5.0————
Qwen/Qwen3.6-27B-FP8
Qwen
5.0————
Qwen/Qwen3.6-35B-A3B-FP8
Qwen
5.0————
Rabinovich/LongLive-2.0-5B-Diffusers
Rabinovich
5.0————
raxtemur/trocr-base-ru
raxtemur
5.0————
realrebelai/JoyAI-Echo_GGUF
realrebelai
5.0————
RedHatAI/gemma-4-31B-it-FP8-block
RedHatAI
5.0————
ResembleAI/chatterbox
ResembleAI
5.0————
rizki-syazali/tapasid_finetuned_itqa
rizki-syazali
5.0————
rtr46/meiki.text.detect.v0
rtr46
5.0————
rtr46/meiki.txt.recognition.v0
rtr46
5.0————
rubentito/layoutlmv3-base-mpdocvqa
rubentito
5.0————
RunDiffusion/Juggernaut-XL-v9
RunDiffusion
5.0————
s-nlp/roberta_toxicity_classifier
s-nlp
5.0————
SadilKhan/NURBGen
SadilKhan
5.0————
Salesforce/blip-image-captioning-base
Salesforce
5.0————
Salesforce/blip-image-captioning-large
Salesforce
5.0————
Salesforce/blip-vqa-base
Salesforce
5.0————
Salesforce/blip-vqa-capfilt-large
Salesforce
5.0————
samandar1105/tablemind-qwen2.5-1.5b
samandar1105
5.0————
SamLowe/roberta-base-go_emotions
SamLowe
5.0————
samuelchristlie/Wan2.1-T2V-1.3B-GGUF
samuelchristlie
5.0————
SantiagoPG/DOC_QA
SantiagoPG
5.0————

3,181–3,240 of 3,712 models · select a column to sort

About this order: Recommended shows our editorial shortlist first, followed by recent releases. The spec score is a 0–100 figure SyncDev calculates from each vendor's published specifications — context window, reasoning support, input modalities, tool calling, maximum output and how recently the model shipped. It measures breadth of capability, not benchmark performance, so a higher-scoring model is not automatically the better choice for your task.