AWQ explained

What AWQ is, which runtimes read it, what it costs in VRAM, and all 53 of the 81 models in this index that ship in it.

What AWQ is

Activation-Aware Weight Quantization. High-accuracy INT4 for NVIDIA. Pairs perfectly with vLLM for server deployment. 53 of the 81 models in this index ship in it, across 1 quant level — INT4.

What reads it

vLLM · AutoAWQ · TGI. Hardware: NVIDIA GPU (CUDA 11.8+). Best suited to: High-throughput API server. Where it is strong: Best accuracy at 4-bit; Blazing fast with vLLM; Excellent batch throughput. Where it is not: NVIDIA only; More setup than GGUF.

What it costs

Llama 3.1 8B Instruct at AWQ INT4 is 4 bits per weight, which works out to 3.8 GB of weights plus 0.5 GB of KV cache at 4K context and a 0.4 GB activation buffer — 4.8 GB in total. The smallest card in this index that clears that comfortably is an RTX 5060 Ti 8G. Across the 53 models here with a published perplexity figure at this level, the median loss against FP16 is 4.0%.

AWQ levels in this index

Levelbits/weightModelsMedian loss
INT44534.0%median of 53

Bits per weight is the model row's own figure, so a range means different models ship the same level at slightly different sizes. The median loss is computed only over the models with a published perplexity figure at that level; the sample size is printed beside it.

Models in this index that ship AWQ

53 of 81, largest first, each with its smallest AWQ level and that level's published perplexity loss where one exists.

Browse AWQ models

Common questions

What is AWQ?

Activation-Aware Weight Quantization. High-accuracy INT4 for NVIDIA. Pairs perfectly with vLLM for server deployment. It is read by vLLM · AutoAWQ · TGI, needs NVIDIA GPU (CUDA 11.8+), and 53 of the 81 models in this index ship in it.

How much VRAM does Llama 3.1 8B Instruct need in AWQ?

About 4.8 GB at AWQ INT4 with a 4K context window — 3.8 GB of that is the weights themselves, so an 8 GB card clears it comfortably. Longer context adds KV cache on top; the calculator will size any combination.

AWQ or something else?

Depends on what reads it — this one belongs where the job is high-throughput API server. This site compares it directly against GGUF, EXL2, using only the models that ship both formats — the only place the comparison is measurable rather than editorial.

AWQ compared with other formats