How much VRAM does Dark-Scarlett-v2.0-31B need?

Q4_K_M is exactly 18,687,063,232 bytes (17.40 GiB) in weights. Add the KV cache, which depends on context length, plus roughly half a gigabyte of runtime overhead.

ReadyArt · text

Dark-Scarlett-v2.0-31B

ReadyArt/Dark-Scarlett-v2.0-31B

Dark-Scarlett-v2.0-31B at Q4_K_M is exactly 18,687,063,232 bytes (17.40 GiB / 18.69 GB) — an effective 4.780 bits per weight, not the nominal 4.

From the file· summed from 1 file(s)

Parameters

31.3B

Architecture

gemma4

Context

—

native (config.json)

License

apache-2.0

Shipped quantizations

● exact bytes, summed from published files

Quant	Size●	Exact bytes●	Effective bpw●	Tensors●	Publisher
Q4_K_M	17.40 GiB	18,687,063,232	4.780	—	ReadyArt
Q5_K_M	20.35 GiB	21,845,570,752	5.588	—	ReadyArt
Q6_K	23.47 GiB	25,201,484,992	6.447	—	ReadyArt
Q8_0	30.39 GiB	32,635,675,840	8.349	—	ReadyArt

Compare with

same modality, comparable size

vs Qwen3-Coder-30B-A3B-Instruct vs Qwen3.6-27B vs Qwen3.8-27B vs gemma-4-E4B-it vs Qwen3-30B-A3B-Thinking-2507 vs Qwen3-4B 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 16.38 GiB. The real file is 17.40 GiB, because a quantization is a mixture and some tensors are always kept at higher precision.

Architecture

Architecture unavailable — this repository is gated and no ungated mirror was found. Exact file sizes above are still authoritative; only the KV math needs the config.

Questions people ask

How much VRAM does Dark-Scarlett-v2.0-31B need?: Q4_K_M is exactly 18,687,063,232 bytes (17.40 GiB) in weights. Add the KV cache, which depends on your context length, plus roughly half a gigabyte of runtime overhead.
Which quantization of Dark-Scarlett-v2.0-31B 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.