How much VRAM does Melody1437-12B need?

Q4_K_M is exactly 8,568,894,048 bytes (7.98 GiB) in weights. Add the KV cache, which depends on context length, plus roughly half a gigabyte of runtime overhead.

ReadyArt · text

Melody1437-12B

ReadyArt/Melody1437-12B

Melody1437-12B at Q4_K_M is exactly 8,568,894,048 bytes (7.98 GiB / 8.57 GB) — an effective 5.732 bits per weight, not the nominal 4.

From the file· summed from 1 file(s)

Parameters

12.0B

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
Q3_K_M	6.77 GiB	7,274,599,008	4.866	—	ReadyArt
Q4_K_M	7.98 GiB	8,568,894,048	5.732	—	ReadyArt
Q5_K_M	9.07 GiB	9,734,779,488	6.512	—	ReadyArt
Q6_K	10.22 GiB	10,973,532,768	7.340	—	ReadyArt
Q8_0	12.68 GiB	13,613,363,808	9.106	—	ReadyArt

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 6.27 GiB. The real file is 7.98 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 Melody1437-12B need?: Q4_K_M is exactly 8,568,894,048 bytes (7.98 GiB) in weights. Add the KV cache, which depends on your context length, plus roughly half a gigabyte of runtime overhead.
Which quantization of Melody1437-12B 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.