GPTQ models for nn.Linear 4bit weight & 16bit activation (symmetric) integer quantization
Karamjot Singh
karamjotsingh
AI & ML interests
Computer Vision, LLM Optimization
Recent Activity
updated a model 23 days ago
karamjotsingh/Llama-3.2-3B-Instruct updated a collection 2 months ago
GPTQ DeepCompressor updated a model 2 months ago
karamjotsingh/gemma-4-E4BOrganizations
models 16
karamjotsingh/Llama-3.2-3B-Instruct
Updated
karamjotsingh/gemma-4-E4B
Updated
karamjotsingh/gemma-4-E2B-it
Updated
karamjotsingh/gemma-4-E2B
Updated
karamjotsingh/Llama-3.1-8B-Instruct
Updated
karamjotsingh/Llama-3.2-1B-Instruct
Updated
karamjotsingh/Qwen3-VL-4B-Instruct
Updated
karamjotsingh/Qwen2.5-VL-3B-Instruct
Updated
karamjotsingh/MultiModalPositionIdDebug
Updated
karamjotsingh/Qwen3-4B-Base
Updated
datasets 0
None public yet