🪐 A curated collection of lightweight multimodal models designed for edge deployment.
Jeremy Live
developerjeremylive
AI & ML interests
Machine Learning Engineer
Recent Activity
upvoted a collection about 6 hours ago
🌪️ Negentropy-claude-opus-4.7 updated a collection about 6 hours ago
Transformers.js V4 demos updated a collection about 6 hours ago
AI locals Models 2026Organizations
spaces 47
pinned
Paused
Agents
Qwen 3.5 HF Demo
🤗
Demo of the Qwen 3.5 Multimodal Model
pinned
Paused
Agents
Flux.2 4B Encoder Comparator
⚡
Faster Decoding - (Small Decoder)
pinned
Paused
MCP
HY World 2.0 Demo
🤗
A Multi-Modal World Model for Reconstruction
pinned
Sleeping
MCP
SAM3-Gemma4-CUDA
⚡
Object Multiplex
pinned
Paused
MCP
TIGER Audio Extractor
✂
Extraction & Reconstruction for Efficient Speech Separation
pinned
Paused
Agents
TADA — Text-Acoustic Dual Alignment for Speech
🗯
Speech generation from text and acoustic reference
models 4
developerjeremylive/Qwopus3.6-35B-A3B-v1-GGUF-etheroi
Image-Text-to-Text • 35B • Updated
developerjeremylive/Gemopus-4-26B-A4B-it-GGUF-etheroi
Text Generation • 25B • Updated • 1.02k
developerjeremylive/sd-x2-latent-upscaler-etheroi
Updated • 9
developerjeremylive/gemma-3b-trafic-vision
Image-Text-to-Text • 5B • Updated • 5
datasets 0
None public yet