Rajkumar rawal
AI & ML interests
Recent Activity
Organizations
- Configuration errorFeatured87
LFM2 WebGPU – In-browser tool calling
🛠87In-browser tool calling, powered by Transformers.js
- Running36
Wllama
🦙36Run GGUF directly on your browser!
-
openai/gpt-oss-120b
Text Generation • 120B • Updated • 4.26M • • 4.63k -
openai/gpt-oss-20b
Text Generation • 22B • Updated • 6.5M • • 4.49k
- PausedFeatured824
Qwen Image Edit
✒824Edit and enhance images based on descriptive instructions
-
Qwen/Qwen-Image-Edit
Image-to-Image • Updated • 70.4k • • 2.35k -
black-forest-labs/FLUX.1-Kontext-dev
Image-to-Image • Updated • 84.1k • • 2.58k - Running on ZeroMCPFeatured1.56k
FLUX.1 Kontext
⚡1.56kKontext image editing on FLUX[dev]
- Runtime error63
DeepseekJanusPro
🚀63Deepseek AI's Janus-Pro-7B: Generate image from text
-
The Leaderboard Illusion
Paper • 2504.20879 • Published • 72 - PausedFeatured824
Qwen Image Edit
✒824Edit and enhance images based on descriptive instructions
- Running on ZeroFeatured903
Qwen Image
🖼903Generate detailed images from your 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 • 175k • 228 -
unsloth/gpt-oss-120b-GGUF
Text Generation • 117B • Updated • 115k • 232 -
unsloth/gpt-oss-20b-GGUF
Text Generation • 21B • Updated • 339k • 647
-
allenai/MolmoAct-Pretraining-Mixture
Viewer • Updated • 24.2M • 2.53k • 10 -
nvidia/Llama-Nemotron-VLM-Dataset-v1
Viewer • Updated • 2.86M • 1.53k • 159 -
zai-org/GLM-4.1V-9B-Thinking
Image-Text-to-Text • 10B • Updated • 437k • 774 - Running on ZeroFeatured194
Chat with Kimi-VL-A3B-Thinking-2506
🤔194Chat with Kimi-VL: respond to text, images, video, PDFs
-
Wan-AI/Wan2.2-T2V-A14B-Diffusers
Text-to-Video • Updated • 108k • • 124 - PausedMCPFeatured514
Wan 2.2 5B
🚀514Generate videos from text prompts and optional images
-
FunAudioLLM/ThinkSound
Video-to-Video • Updated • 52 - PausedMCPFeatured318
ThinkSound
🔊318Generate audio for a silent video using text prompts
- RunningFeatured28
HunyuanWorld Viewer
📊28Explore 3D worlds by selecting examples or uploading files
-
tencent/HunyuanWorld-1
Image-to-3D • Updated • 6.71k • 419 - Paused3.24k
Hunyuan3D-2.0
🌍3.24kText-to-3D and Image-to-3D Generation
- PausedFeatured2.13k
Hunyuan3D-2.1
👻2.13kImage-to-3D Generation
-
The Leaderboard Illusion
Paper • 2504.20879 • Published • 72 -
SmolVLM: Redefining small and efficient multimodal models
Paper • 2504.05299 • Published • 207 -
Seedance 1.0: Exploring the Boundaries of Video Generation Models
Paper • 2506.09113 • Published • 108 -
Small Language Models are the Future of Agentic AI
Paper • 2506.02153 • Published • 24
- 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 • 175k • 228 -
unsloth/gpt-oss-120b-GGUF
Text Generation • 117B • Updated • 115k • 232 -
unsloth/gpt-oss-20b-GGUF
Text Generation • 21B • Updated • 339k • 647
-
allenai/MolmoAct-Pretraining-Mixture
Viewer • Updated • 24.2M • 2.53k • 10 -
nvidia/Llama-Nemotron-VLM-Dataset-v1
Viewer • Updated • 2.86M • 1.53k • 159 -
zai-org/GLM-4.1V-9B-Thinking
Image-Text-to-Text • 10B • Updated • 437k • 774 - Running on ZeroFeatured194
Chat with Kimi-VL-A3B-Thinking-2506
🤔194Chat with Kimi-VL: respond to text, images, video, PDFs
-
Wan-AI/Wan2.2-T2V-A14B-Diffusers
Text-to-Video • Updated • 108k • • 124 - PausedMCPFeatured514
Wan 2.2 5B
🚀514Generate videos from text prompts and optional images
-
FunAudioLLM/ThinkSound
Video-to-Video • Updated • 52 - PausedMCPFeatured318
ThinkSound
🔊318Generate audio for a silent video using text prompts
- Configuration errorFeatured87
LFM2 WebGPU – In-browser tool calling
🛠87In-browser tool calling, powered by Transformers.js
- Running36
Wllama
🦙36Run GGUF directly on your browser!
-
openai/gpt-oss-120b
Text Generation • 120B • Updated • 4.26M • • 4.63k -
openai/gpt-oss-20b
Text Generation • 22B • Updated • 6.5M • • 4.49k
- RunningFeatured28
HunyuanWorld Viewer
📊28Explore 3D worlds by selecting examples or uploading files
-
tencent/HunyuanWorld-1
Image-to-3D • Updated • 6.71k • 419 - Paused3.24k
Hunyuan3D-2.0
🌍3.24kText-to-3D and Image-to-3D Generation
- PausedFeatured2.13k
Hunyuan3D-2.1
👻2.13kImage-to-3D Generation
- PausedFeatured824
Qwen Image Edit
✒824Edit and enhance images based on descriptive instructions
-
Qwen/Qwen-Image-Edit
Image-to-Image • Updated • 70.4k • • 2.35k -
black-forest-labs/FLUX.1-Kontext-dev
Image-to-Image • Updated • 84.1k • • 2.58k - Running on ZeroMCPFeatured1.56k
FLUX.1 Kontext
⚡1.56kKontext image editing on FLUX[dev]
-
The Leaderboard Illusion
Paper • 2504.20879 • Published • 72 -
SmolVLM: Redefining small and efficient multimodal models
Paper • 2504.05299 • Published • 207 -
Seedance 1.0: Exploring the Boundaries of Video Generation Models
Paper • 2506.09113 • Published • 108 -
Small Language Models are the Future of Agentic AI
Paper • 2506.02153 • Published • 24
- Runtime error63
DeepseekJanusPro
🚀63Deepseek AI's Janus-Pro-7B: Generate image from text
-
The Leaderboard Illusion
Paper • 2504.20879 • Published • 72 - PausedFeatured824
Qwen Image Edit
✒824Edit and enhance images based on descriptive instructions
- Running on ZeroFeatured903
Qwen Image
🖼903Generate detailed images from your text prompts