PocketWeights

community

AI & ML interests

Heavy models, made light. We design, synthesize, and optimize domain-specialized LLMs and curated GGUFs for local developers, edge devices, and 6GB–16GB VRAM hardware.

Recent Activity

PocketWeightsLabs updated a model about 2 months ago

PocketWeights/PocketWeights-Qwen2.5-7B-Instruct

PocketWeightsLabs published a model about 2 months ago

PocketWeights/PocketWeights-Qwen2.5-7B-Instruct

PocketWeightsLabs updated a model about 2 months ago

PocketWeights/PocketWeights-Qwen2.5-1.5B-Instruct

View all activity

models 14

PocketWeights/PocketWeights-Qwen2.5-7B-Instruct

8B • Updated Sep 7 • 35

PocketWeights/PocketWeights-Qwen2.5-1.5B-Instruct

Text Generation • 2B • Updated Sep 6 • 32

PocketWeights/PocketWeights-Qwen2.5-0.5B-GGUF

Text Generation • 0.5B • Updated Sep 1 • 107

PocketWeights/PocketWeights-Qwen2.5-1.5B-GGUF

Text Generation • 2B • Updated Sep 1 • 69

PocketWeights/PocketWeights-Qwen2.5-14B-Coder-Creative-GGUF

Text Generation • 15B • Updated Aug 30 • 168

PocketWeights/PocketWeights-Qwen2.5-14B-Coder-Creative

Text Generation • 15B • Updated Aug 30 • 61

PocketWeights/DeepSeek-R1-Llama-8B-Abliterated-GGUF

Text Generation • 8B • Updated Aug 27 • 168

PocketWeights/Qwen3.8-27B-WebGGUF

Text Generation • 27B • Updated Aug 27 • 182

PocketWeights/Muse-Glimmer-30B-WebGGUF

Text Generation • 28B • Updated Aug 27 • 26

PocketWeights/Gliese-Qwen3.5-9B-Abliterated-WebGGUF

Image-Text-to-Text • 9B • Updated Aug 27 • 125 • 1

datasets 0

None public yet