Need English-only (or minimal multilingual) 2B-4B LLM for Agentic AI on GTX 1660 Super (6GB VRAM) – quantization friendly

I also personally recommend these models:

huggingface.co

unsloth/gemma-4-E2B-it-GGUF · Hugging Face

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

huggingface.co

unsloth/Qwen3.5-4B-GGUF · Hugging Face

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

huggingface.co

LiquidAI/LFM2.5-1.2B-Instruct · Hugging Face

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

huggingface.co

HuggingFaceTB/SmolLM3-3B · Hugging Face

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

huggingface.co

unsloth/granite-4.1-3b-GGUF · Hugging Face

We’re on a journey to advance and democratize artificial intelligence through open source and open science.