Rajkumar rawal
AI & ML interests
Recent Activity
Organizations
- RunningFeatured93
LFM2 WebGPU – In-browser tool calling
🛠93In-browser tool calling, powered by Transformers.js
- Running40
Wllama
🦙40Run GGUF directly on your browser!
-
openai/gpt-oss-120b
Text Generation • 117B • Updated • 4.22M • • 5.1k -
openai/gpt-oss-20b
Text Generation • 22B • Updated • 8.1M • • 4.91k
- Running on ZeroAgentsFeatured849
Qwen Image Edit
✒849Edit images using natural language instructions
-
Qwen/Qwen-Image-Edit
Image-to-Image • 20B • Updated • 104k • • 2.48k -
black-forest-labs/FLUX.1-Kontext-dev
Image-to-Image • 12B • Updated • 231k • • 2.77k - Running on ZeroMCPFeatured1.61k
FLUX.1 Kontext
⚡1.61kKontext 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 ZeroAgentsFeatured849
Qwen Image Edit
✒849Edit images using natural language instructions
- Running on ZeroAgentsFeatured920
Qwen Image
🖼920Generate 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 • 17.5k • 235 -
unsloth/gpt-oss-120b-GGUF
Text Generation • 117B • Updated • 106k • 288 -
unsloth/gpt-oss-20b-GGUF
Text Generation • 21B • Updated • 542k • 774
-
Wan-AI/Wan2.2-T2V-A14B-Diffusers
Text-to-Video • 14B • Updated • 94.2k • • 154 -
FunAudioLLM/ThinkSound
Video-to-Video • Updated • 54 - PausedMCPFeatured320
ThinkSound
🔊320Generate audio for a silent video using text prompts
- RunningAgents84
Wan2.1 Fun 1.3B InP
📈84Generate images using text prompts
- RunningFeatured29
HunyuanWorld Viewer
📊29Explore 3D worlds by selecting examples or uploading files
-
tencent/HunyuanWorld-1
Image-to-3D • Updated • 5.69k • 603 - Running on ZeroAgents3.36k
Hunyuan3D-2.0
🌍3.36kText-to-3D and Image-to-3D Generation
- Running on ZeroAgentsFeatured2.18k
Hunyuan3D-2.1
👻2.18kImage-to-3D Generation
-
The Leaderboard Illusion
Paper • 2504.20879 • Published • 71 -
SmolVLM: Redefining small and efficient multimodal models
Paper • 2504.05299 • Published • 211 -
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 • 17.5k • 235 -
unsloth/gpt-oss-120b-GGUF
Text Generation • 117B • Updated • 106k • 288 -
unsloth/gpt-oss-20b-GGUF
Text Generation • 21B • Updated • 542k • 774
-
Wan-AI/Wan2.2-T2V-A14B-Diffusers
Text-to-Video • 14B • Updated • 94.2k • • 154 -
FunAudioLLM/ThinkSound
Video-to-Video • Updated • 54 - PausedMCPFeatured320
ThinkSound
🔊320Generate audio for a silent video using text prompts
- RunningAgents84
Wan2.1 Fun 1.3B InP
📈84Generate images using text prompts
- RunningFeatured93
LFM2 WebGPU – In-browser tool calling
🛠93In-browser tool calling, powered by Transformers.js
- Running40
Wllama
🦙40Run GGUF directly on your browser!
-
openai/gpt-oss-120b
Text Generation • 117B • Updated • 4.22M • • 5.1k -
openai/gpt-oss-20b
Text Generation • 22B • Updated • 8.1M • • 4.91k
- RunningFeatured29
HunyuanWorld Viewer
📊29Explore 3D worlds by selecting examples or uploading files
-
tencent/HunyuanWorld-1
Image-to-3D • Updated • 5.69k • 603 - Running on ZeroAgents3.36k
Hunyuan3D-2.0
🌍3.36kText-to-3D and Image-to-3D Generation
- Running on ZeroAgentsFeatured2.18k
Hunyuan3D-2.1
👻2.18kImage-to-3D Generation
- Running on ZeroAgentsFeatured849
Qwen Image Edit
✒849Edit images using natural language instructions
-
Qwen/Qwen-Image-Edit
Image-to-Image • 20B • Updated • 104k • • 2.48k -
black-forest-labs/FLUX.1-Kontext-dev
Image-to-Image • 12B • Updated • 231k • • 2.77k - Running on ZeroMCPFeatured1.61k
FLUX.1 Kontext
⚡1.61kKontext image editing on FLUX[dev]
-
The Leaderboard Illusion
Paper • 2504.20879 • Published • 71 -
SmolVLM: Redefining small and efficient multimodal models
Paper • 2504.05299 • Published • 211 -
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 ZeroAgentsFeatured849
Qwen Image Edit
✒849Edit images using natural language instructions
- Running on ZeroAgentsFeatured920
Qwen Image
🖼920Generate high-quality images from text prompts