Rajkumar rawal
AI & ML interests
Recent Activity
Organizations
- RunningFeatured94
LFM2 WebGPU – In-browser tool calling
🛠94In-browser tool calling, powered by Transformers.js
- Running41
Wllama
🦙41Run GGUF directly on your browser!
-
openai/gpt-oss-120b
Text Generation • 117B • Updated • 4.56M • • 5.31k -
openai/gpt-oss-20b
Text Generation • 21B • Updated • 6.77M • • 5.1k
- Running on ZeroAgentsFeatured868
Qwen Image Edit
✒868Edit images using natural language instructions
-
Qwen/Qwen-Image-Edit
Image-to-Image • 20B • Updated • 117k • • 2.53k -
black-forest-labs/FLUX.1-Kontext-dev
Image-to-Image • 12B • Updated • 350k • • 2.85k - Running on ZeroMCPFeatured1.63k
FLUX.1 Kontext
⚡1.63kKontext image editing on FLUX[dev]
- Running on ZeroAgents63
DeepseekJanusPro
🚀63Deepseek AI's Janus-Pro-7B: Generate image from text
-
The Leaderboard Illusion
Paper • 2504.20879 • Published • 71 - Running on ZeroAgentsFeatured868
Qwen Image Edit
✒868Edit images using natural language instructions
- Running on ZeroAgentsFeatured925
Qwen Image
🖼925Generate high-quality images from text prompts
- Running2
Full-Stack Fine-Tuning for Q
🧠2Full-Stack Fine-Tuning for the Q Programming Language
-
nvidia/Llama-3_3-Nemotron-Super-49B-v1_5
Text Generation • 50B • Updated • 42.2k • 235 -
unsloth/gpt-oss-120b-GGUF
Text Generation • 117B • Updated • 72.8k • 296 -
unsloth/gpt-oss-20b-GGUF
Text Generation • 21B • Updated • 511k • 843
-
Wan-AI/Wan2.2-T2V-A14B-Diffusers
Text-to-Video • 14B • Updated • 139k • • 158 -
FunAudioLLM/ThinkSound
Video-to-Video • Updated • 56 - PausedMCPFeatured321
ThinkSound
🔊321Generate audio for a silent video using text prompts
- RunningAgents85
Wan2.1 Fun 1.3B InP
📈85Generate images using text prompts
- RunningFeatured29
HunyuanWorld Viewer
📊29Explore 3D worlds by selecting examples or uploading files
-
tencent/HunyuanWorld-1
Image-to-3D • Updated • 4.82k • 605 - Running on ZeroAgents3.39k
Hunyuan3D-2.0
🌍3.39kText-to-3D and Image-to-3D Generation
- Running on ZeroAgentsFeatured2.26k
Hunyuan3D-2.1
👻2.26kImage-to-3D Generation
-
The Leaderboard Illusion
Paper • 2504.20879 • Published • 71 -
SmolVLM: Redefining small and efficient multimodal models
Paper • 2504.05299 • Published • 212 -
Seedance 1.0: Exploring the Boundaries of Video Generation Models
Paper • 2506.09113 • Published • 109 -
Small Language Models are the Future of Agentic AI
Paper • 2506.02153 • Published • 25
- Running2
Full-Stack Fine-Tuning for Q
🧠2Full-Stack Fine-Tuning for the Q Programming Language
-
nvidia/Llama-3_3-Nemotron-Super-49B-v1_5
Text Generation • 50B • Updated • 42.2k • 235 -
unsloth/gpt-oss-120b-GGUF
Text Generation • 117B • Updated • 72.8k • 296 -
unsloth/gpt-oss-20b-GGUF
Text Generation • 21B • Updated • 511k • 843
-
Wan-AI/Wan2.2-T2V-A14B-Diffusers
Text-to-Video • 14B • Updated • 139k • • 158 -
FunAudioLLM/ThinkSound
Video-to-Video • Updated • 56 - PausedMCPFeatured321
ThinkSound
🔊321Generate audio for a silent video using text prompts
- RunningAgents85
Wan2.1 Fun 1.3B InP
📈85Generate images using text prompts
- RunningFeatured94
LFM2 WebGPU – In-browser tool calling
🛠94In-browser tool calling, powered by Transformers.js
- Running41
Wllama
🦙41Run GGUF directly on your browser!
-
openai/gpt-oss-120b
Text Generation • 117B • Updated • 4.56M • • 5.31k -
openai/gpt-oss-20b
Text Generation • 21B • Updated • 6.77M • • 5.1k
- RunningFeatured29
HunyuanWorld Viewer
📊29Explore 3D worlds by selecting examples or uploading files
-
tencent/HunyuanWorld-1
Image-to-3D • Updated • 4.82k • 605 - Running on ZeroAgents3.39k
Hunyuan3D-2.0
🌍3.39kText-to-3D and Image-to-3D Generation
- Running on ZeroAgentsFeatured2.26k
Hunyuan3D-2.1
👻2.26kImage-to-3D Generation
- Running on ZeroAgentsFeatured868
Qwen Image Edit
✒868Edit images using natural language instructions
-
Qwen/Qwen-Image-Edit
Image-to-Image • 20B • Updated • 117k • • 2.53k -
black-forest-labs/FLUX.1-Kontext-dev
Image-to-Image • 12B • Updated • 350k • • 2.85k - Running on ZeroMCPFeatured1.63k
FLUX.1 Kontext
⚡1.63kKontext image editing on FLUX[dev]
-
The Leaderboard Illusion
Paper • 2504.20879 • Published • 71 -
SmolVLM: Redefining small and efficient multimodal models
Paper • 2504.05299 • Published • 212 -
Seedance 1.0: Exploring the Boundaries of Video Generation Models
Paper • 2506.09113 • Published • 109 -
Small Language Models are the Future of Agentic AI
Paper • 2506.02153 • Published • 25
- Running on ZeroAgents63
DeepseekJanusPro
🚀63Deepseek AI's Janus-Pro-7B: Generate image from text
-
The Leaderboard Illusion
Paper • 2504.20879 • Published • 71 - Running on ZeroAgentsFeatured868
Qwen Image Edit
✒868Edit images using natural language instructions
- Running on ZeroAgentsFeatured925
Qwen Image
🖼925Generate high-quality images from text prompts