The SyncDev models directory

AI Models Directory

Find the right model for the work you need to do. Explore 3,077 profiles, from hosted language models to image, audio and video generators and downloadable checkpoints.

Explore all models · Page 31

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.

Lightricks/LTX-2.3-22b-IC-LoRA-Colorization
Lightricks
10.0————
Lightricks/LTX-2.3-22b-IC-LoRA-Day-To-Night
Lightricks
10.0————
Lightricks/LTX-2.3-22b-IC-LoRA-Deblur
Lightricks
10.0————
Lightricks/LTX-2.3-22b-IC-LoRA-Decompression
Lightricks
10.0————
Lightricks/LTX-2.3-22b-IC-LoRA-HDR
Lightricks
10.0————
Lightricks/LTX-2.3-22b-IC-LoRA-In-Outpainting
Lightricks
10.0————
Lightricks/LTX-2.3-22b-IC-LoRA-Ingredients
Lightricks
10.0————
Lightricks/LTX-2.3-22b-IC-LoRA-Instant-Shave
Lightricks
10.0————
Lightricks/LTX-2.3-22b-IC-LoRA-Pixel-Spatial-Upscaler
Lightricks
10.0————
Lightricks/LTX-2.3-22b-IC-LoRA-Water-Simulation
Lightricks
10.0————
Lightricks/LTX-2.3-fp8
Lightricks
10.0————
Lightricks/LTX-2.3-nvfp4
Lightricks
10.0————
Lightricks/LTX-Video
Lightricks
10.0————
Lightricks/LTX-Video-ICLoRA-detailer-13b-0.9.8
Lightricks
5.0————
lightx2v/Qwen-Image-Edit-2511-Lightning
lightx2v
10.0————
lightx2v/Qwen-Image-Edit-Causal
lightx2v
10.0————
lightx2v/Qwen-Image-Lightning
lightx2v
5.0————
lightx2v/Wan2.2-Distill-Loras
lightx2v
10.0————
LiheYoung/depth_anything_vitb14
LiheYoung
10.0————
LiheYoung/depth_anything_vitl14
LiheYoung
10.0————
LiheYoung/depth_anything_vits14
LiheYoung
10.0————
LiheYoung/depth-anything-base-hf
LiheYoung
10.0————
LiheYoung/depth-anything-large-hf
LiheYoung
10.0————
LiheYoung/depth-anything-small-hf
LiheYoung
10.0————
lilylilith/AnyPose
lilylilith
10.0————
lilylilith/QIE-2511-MP-AnyLight
lilylilith
10.0————
Ling 2.6 1t
Novita via Requesty
30.2262.14K$0.30$2.50—
Ling 2.6 1T
inclusionAI
20.2262.14K———
Ling 2.6 Flash
inclusionAI
16.8131.07K———
Ling 2.6 Flash
Novita via Requesty
30.2262.14K$0.10$0.30—
Ling 3.0 Tiny
inclusionAI
31.8131.07K———
lintw/HealthGPT-Pro-27B
lintw
10.0————
lintw/HealthGPT-Pro-4B
lintw
10.0————
lintw/HealthGPT-Pro-8B
lintw
10.0————
LiquidAI/LFM2.5-Audio-1.5B
Liquid AI
10.0————
LiquidAI/LFM2.5-Audio-1.5B-JP-GGUF
Liquid AI
10.0————
Lisibonny/modelo_qa_beto_squad_es_pdqa
Lisibonny
0.0————
litert-community/SAM2.1-Hiera-Tiny-Mask-Decoder
litert-community
10.0————
liuxin9494/Qwen-Image-Edit-Rapid-AIO-GGUF-mirror
liuxin9494
10.0————
livekit/turn-detector
livekit
5.0————
Llama 3.1 8b Instruct
Novita via Requesty
6.816.38K$0.05$0.05—
Llama 3.2 90B Vision Instruct
Deepinfra via Requesty
23.4131.07K$0.35$0.40—
Llama 3.3 70B Instruct Turbo
Deepinfra via Requesty
31.8131.07K$0.12$0.30—
Llama 4 Maverick 17b 128e Instruct Fp8
Novita via Requesty
36.91.05M$0.20$0.85—
llava-hf/llava-1.5-7b-hf
llava-hf
5.0————
llava-hf/LLaVA-NeXT-Video-7B-hf
llava-hf
5.0————
lllyasviel/sd-controlnet-canny
lllyasviel
10.0————
lllyasviel/sd-controlnet-openpose
lllyasviel
10.0————
llmfan46/gemma-4-E4B-it-ultra-uncensored-heretic-GGUF
llmfan46
20.0————
llmfan46/gemma-4-E4B-it-uncensored-heretic
llmfan46
20.0————
lmg-anon/vntl-llama3-8b-v2-gguf
lmg-anon
0.0————
lmms-lab/LLaVA-Video-7B-Qwen2
lmms-lab
5.0————
lmstudio-community/gemma-4-12B-it-MLX-4bit
lmstudio-community
20.0————
lmstudio-community/gemma-4-12B-it-MLX-5bit
lmstudio-community
20.0————
lmstudio-community/gemma-4-12B-it-MLX-6bit
lmstudio-community
20.0————
lmstudio-community/gemma-4-12B-it-MLX-8bit
lmstudio-community
20.0————
lmstudio-community/gemma-4-E2B-it-MLX-4bit
lmstudio-community
20.0————
lmstudio-community/gemma-4-E2B-it-MLX-5bit
lmstudio-community
20.0————
lmstudio-community/gemma-4-E2B-it-MLX-6bit
lmstudio-community
20.0————
lmstudio-community/gemma-4-E2B-it-MLX-8bit
lmstudio-community
20.0————

1801–1860 of 3077 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.