Local AI · No Cloud Required

Can your laptop actually run that model?

A viral post claimed a free 9-billion-parameter model built an app offline — no API bill, no cloud. The real gatekeeper for local AI is memory. Use this calculator to see exactly what fits on your machine.

Estimated memory needed6.1 GB61% of your 10 GB
Drag to rotate the memory stack

The math is simpler than you think

01 Weights dominate

Every parameter is stored as a number. At FP16 that is 2 bytes per parameter, so a 9B model needs about 9 × 2 = 18 GB just for weights. Quantize to 4-bit (~0.55 bytes with overhead) and the same model shrinks to roughly 9 × 0.55 ≈ 5 GB — a 3.6× reduction with only a small quality dip.

02 KV cache grows with context

While generating, the model caches attention keys and values for every token in context. For a typical 9B architecture that costs roughly 0.15 MB per token. An 8K context adds ~1.2 GB; a 128K context can add more than the weights themselves. Long context is a memory feature, not a free lunch.

03 Why "self-fixing loops" work locally

Agentic coding models run plan → write → test → fix cycles. Locally, each retry costs zero API dollars — only electricity and time. A loop that takes 40 attempts at $0.02 per call would cost $0.80 in the cloud; locally it costs nothing, which changes how aggressively you can let an agent iterate.

04 Tokens per second reality

Speed scales with memory bandwidth. A laptop with 100 GB/s bandwidth running a 5 GB (Q4) model tops out near 100 ÷ 5 = 20 tokens/sec. The same laptop on an 18 GB FP16 model crawls at ~5.5 tokens/sec. Quantization is a speed upgrade, not just a size trick.

ModelFP16Q8Q4Runs on 16 GB laptop?
3B6 GB3 GB1.7 GBYes, easily
9B18 GB9 GB5 GBYes at Q8/Q4
34B68 GB34 GB19 GBNo (needs ~24 GB)
70B140 GB70 GB39 GBNo (workstation class)

Quick check

A 12B model at Q4 (~0.55 bytes/param) with a small context needs roughly how much memory?

Enjoy this tool? Build your own with Super