LLM Parameters to INT4 Quant VRAM Calculator

70B at INT4: ~35 GB — barely fits on a single A100-80GB. At FP16 the same model needs 140 GB: two A100s at $6/hr each. Quantization stopped being about accuracy tradeoffs. Now it is about whether your model fits on a GPU at all.

🗜️ Quantization Configuration

Specify your model and quantization parameters. The engine computes compressed weights, scale factor overhead, and compares against the FP16 baseline.

e.g. Llama-2-70B → 70
INT4=4, INT8=8
GPTQ/AWQ group size

INT4 Quantization: How 4-Bit Compression Shrinks LLM VRAM Footprints

Post-training quantization (PTQ) at 4-bit precision is the dominant strategy for running large language models on consumer and prosumer GPUs. Techniques like GPTQ (Generative Pre-Trained Transformer Quantization) and AWQ (Activation-Aware Weight Quantization) compress model weights from 16 bits to 4 bits — a 4× reduction — with minimal perplexity degradation. However, quantization introduces a second memory cost: scale factors stored at higher precision that grow as group size decreases.

How This Calculator Works

This tool models the two-component memory footprint of a group-wise quantized model:

ComponentFormulaDescription
Quantized WeightsParameters × Precision Bits ÷ 8The compressed weight matrix. At 4 bits, a 70B model stores weights in 35 GiB instead of 140 GiB at FP16 — a 75% reduction.
Scale Overhead(Parameters ÷ Group Size) × 2 bytesEach group of weights shares a 16-bit floating-point scale factor. Smaller group sizes improve accuracy but increase scale memory. At group size 128, a 70B model has ~546 million scale factors consuming ~1.02 GiB. At group size 32, that jumps to ~4.07 GiB.
Total VRAM(Quantized Weights + Scale Overhead) × 1.15A 15% overhead buffer accounts for activation memory, CUDA context, and the inference framework runtime (e.g., ExLlamaV2, AutoGPTQ).

Group Size Trade-Off: Accuracy vs. Memory

Group size is the central tuning knob in GPTQ/AWQ quantization. It defines how many weights share a single scale factor, creating a direct accuracy-memory trade-off:

Group SizeScale Overhead (70B Model)Accuracy ImpactUse Case
32~4.07 GiBNegligible perplexity increase. Near-FP16 quality.High-quality chat, code generation, academic benchmarks.
64~2.04 GiBVery minor perplexity increase (~0.1–0.3 PPL).General-purpose inference, acceptable for most production use cases.
128~1.02 GiBModerate perplexity increase (~0.3–0.8 PPL). Standard GPTQ default.Consumer GPU deployment, throughput-optimized serving.
256~0.51 GiBNoticeable degradation on reasoning tasks.Extreme compression, edge devices.

INT4 vs. FP16: The Memory Savings Reality

While INT4 theoretically reduces weight memory by 75%, the effective VRAM savings are typically 65–72% once scale factors and runtime overhead are accounted for. This is still transformative: a 70B model that requires 2–4 A100 GPUs at FP16 can fit on a single RTX 4090 (24 GB) or dual RTX 3090s at INT4. For local inference enthusiasts and small teams, INT4 quantization is the only practical path to running frontier-scale models without enterprise GPU clusters.

Quantization Formats: GPTQ vs. AWQ vs. GGUF

Several INT4 quantization ecosystems exist, each with different trade-offs: