Running
FastVLM CPU Inference Demo
⚡
Real-time VLM model on CPU — 1.4 sec ttft inference
Ajay Kumar
musk12
AI & ML interests
ML Engineer & AI Systems Developer specializing in Generative AI, Computer Vision, and high-performance Deep Learning systems.
Recent Activity
updated a model 8 days ago
musk12/apple-fastvlm-qwen2-q4-gguf updated a model 8 days ago
musk12/apple-fastvlm-cpu-inference-models published a model 8 days ago
musk12/apple-fastvlm-cpu-inference-modelsOrganizations
None yet
spaces 25
Paused
Fastvlm Fast Inference On Cpu
💻
MobileCLIP-L (FastViT) + Qwen2-0.5B inference on CPU
Sleeping
Fastvlm Inference Using Onnx And Gguf
🏢
A fast CPU-optimized Fast VLM using ONNX & GGUF quantization
Sleeping
New Ipl Dash AI
🚀
new-ipl-dash-AI
Sleeping
Agents
Hindi GPT Model Built From Scratch
❓
A custom GPT architecture developed from scratch by Ajay.
Sleeping
Food Image Retrieval AI
🍔
Food Image Retrieval using image embeddings generated by vit
models 15
musk12/apple-fastvlm-qwen2-q4-gguf
Text Generation • 0.6B • Updated • 433
musk12/apple-fastvlm-cpu-inference-models
Image-Text-to-Text • 0.6B • Updated • 223
musk12/apple-fastvlm-vision-encoder-1024
Image Feature Extraction • Updated
musk12/apple-fastvlm-vision-projector-512
Image Feature Extraction • Updated
musk12/fastvlm-qwen2-bf16
Text Generation • 0.6B • Updated • 112
musk12/qwen2_to_gguf_converted_model
0.6B • Updated • 4 • 1
musk12/output_q4_0_gguf
0.6B • Updated • 5
musk12/local_llama_chat_q4
Updated
musk12/index-embeddings-file-vit
Updated
musk12/HindiGPT-v1-base-pretrained
Updated
datasets 0
None public yet