How much VRAM does falcon-mamba-7b-instruct need?

Q4_K_M is exactly 4,204,230,784 bytes (3.92 GiB) in weights. Add the KV cache, which depends on context length, plus roughly half a gigabyte of runtime overhead.

tiiuae · text

falcon-mamba-7b-instruct

tiiuae/falcon-mamba-7b-instruct

falcon-mamba-7b-instruct at Q4_K_M is exactly 4,204,230,784 bytes (3.92 GiB / 4.20 GB) — an effective 4.625 bits per weight, not the nominal 4.

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

Parameters

7.3B

Architecture

mamba

64 layers

Context

—

native (config.json)

License

other

Shipped quantizations

● exact bytes, summed from published files

Quant	Size●	Exact bytes●	Effective bpw●	Tensors●	Publisher
Q4_K_M	3.92 GiB	4,204,230,784	4.625	—	tiiuae

Compare with

same modality, comparable size

vs Qwen3-Coder-30B-A3B-Instruct vs Qwen3.6-27B vs Qwen3.8-27B vs gemma-4-12B-it-qat-q4_0-unquantized vs gemma-4-E4B-it vs Qwen3-30B-A3B-Thinking-2507 All alternatives →Will it fit on my card? →

Why other calculators give a different number

A parameters × bits ÷ 8 estimate puts Q4_K_M at roughly 3.81 GiB. The real file is 3.92 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

4096

Vocab

65,024

Sliding window

none

SWA period

—

MLA

Experts

—

Experts per token

—

use_sliding_window

—

Questions people ask

How much VRAM does falcon-mamba-7b-instruct need?: Q4_K_M is exactly 4,204,230,784 bytes (3.92 GiB) in weights. Add the KV cache, which depends on your context length, plus roughly half a gigabyte of runtime overhead.
Which quantization of falcon-mamba-7b-instruct 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.