Loading listing…
gptq
Security scan passedPost-training 4-bit quantization for LLMs with minimal accuracy loss.
Part of AI Research Skills (Orchestra)Pack · 98 skills
by Orchestra-Research· AI & agentsUnclaimed · Yours? Claim it
What gptq does
About
Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity degradation, or for faster inference (3-4× speedup) vs FP16. Integrates with transformers and PEFT for QLoRA fine-tuning.
Install gptq
More from AI & agents
Skills people install alongside gptq.
