cyankiwi/Qwen3.5-9B-AWQ-4bit
Image-Text-to-Text • 10B • Updated • 363k • 36
Production-Ready Quantized Chat LLMs — 4-bit & 8-bit
FP8, AWQ-4Bit and W8A8 quantized versions of popular models. Lower VRAM, same production quality. Deploy at hexgrid.cloud in one click.
-
-
lovedheart/Qwen3.5-9B-FP8
Image-Text-to-Text • 10B • Updated • 41.1k • 14 -
cyankiwi/Qwen3.5-27B-AWQ-4bit
Image-Text-to-Text • 29B • Updated • 425k • 42 -
RedHatAI/gemma-4-31B-it-FP8-block
Image-Text-to-Text • 31B • Updated • 4.95M • 44 -
QuantTrio/gemma-4-31B-it-AWQ
Image-Text-to-Text • 31B • Updated • 252k • 14 -
nvidia/Llama-3.3-70B-Instruct-FP8
71B • Updated • 126k • 27 -
ibnzterrell/Meta-Llama-3.3-70B-Instruct-AWQ-INT4
Text Generation • 71B • Updated • 87.8k • 30 -
nvidia/Llama-3.1-8B-Instruct-FP8
Text Generation • 8B • Updated • 75k • • 36 -
hugging-quants/Meta-Llama-3.1-8B-Instruct-AWQ-INT4
Text Generation • 8B • Updated • 154k • 92