How much VRAM does moondream2 need?

F16 is exactly 2,839,534,976 bytes (2.64 GiB) in weights. Add the KV cache, which depends on context length, plus roughly half a gigabyte of runtime overhead.

vikhyatk · text

moondream2

vikhyatk/moondream2

moondream2 at F16 is exactly 2,839,534,976 bytes (2.64 GiB / 2.84 GB) — an effective 11.787 bits per weight, not the nominal 1.

From the file· summed from 1 file(s)From the file· KV per layer

Parameters

1.9B

Architecture

phi2

null layers

Context

—

native (config.json)

License

apache-2.0

Shipped quantizations

● exact bytes, summed from published files

Quant	Size●	Exact bytes●	Effective bpw●	Tensors●	Publisher
F16	2.64 GiB	2,839,534,976	11.787	—	cjpais

Compare with

same modality, comparable size

vs gemma-4-12B-it-qat-q4_0-unquantized vs gemma-4-E4B-it vs Qwen3-4B vs Qwen3-8B vs Llama-3.2-1B-Instruct vs llama-3-youko-8b All alternatives →Will it fit on my card? →

Why other calculators give a different number

A parameters × bits ÷ 8 estimate puts F16 at roughly 1.01 GiB. The real file is 2.64 GiB, because a quantization is a mixture and some tensors are always kept at higher precision.

Architecture

from config.json

Layers

—

Attention heads

—

KV heads

—

Head dim

—

Hidden size

—

Vocab

—

Sliding window

none

SWA period

—

MLA

Experts

—

Experts per token

—

use_sliding_window

—

Questions people ask

How much VRAM does moondream2 need?: F16 is exactly 2,839,534,976 bytes (2.64 GiB) in weights. Add the KV cache, which depends on your context length, plus roughly half a gigabyte of runtime overhead.
Which quantization of moondream2 should I use?: Q4_K_M is the usual default. Pick the largest quantization that fits your card at the context you actually need — the table above gives exact sizes for every one published.