Quantization, Mapped: Weights, Activations, KV Cache
What can be quantized in a model, what each saves (memory, bandwidth, compute), and what each risks, with Qwen3-8B's numbers.
overview
1 post
1 post
What can be quantized in a model, what each saves (memory, bandwidth, compute), and what each risks, with Qwen3-8B's numbers.