How much VRAM does L3-Dark-Planet-8B need?

Q4_K_M is exactly 5,113,631,072 bytes (4.76 GiB) in weights. Add the KV cache, which depends on context length, plus roughly half a gigabyte of runtime overhead.

How large is L3-Dark-Planet-8B's KV cache?

4.00 GiB at 32K context with an f16 cache, computed per layer from the model's architecture. Quantizing the cache to q8_0 roughly halves it.

DavidAU · text

L3-Dark-Planet-8B

DavidAU/L3-Dark-Planet-8B

L3-Dark-Planet-8B at Q4_K_M is exactly 5,113,631,072 bytes (4.76 GiB / 5.11 GB) — an effective 5.094 bits per weight, not the nominal 4. Its KV cache at 32K is 4.00 GiB.

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

Parameters

8.0B

Architecture

llama

32 layers

Context

8,192

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_S	3.60 GiB	3,861,500,256	3.847	—	DavidAU
Q3_K_M	3.93 GiB	4,215,918,944	4.200	—	DavidAU
Q3_K_L	4.21 GiB	4,518,957,408	4.502	—	DavidAU
Q4_K_S	4.55 GiB	4,885,565,792	4.867	—	DavidAU
Q4_K_M	4.76 GiB	5,113,631,072	5.094	—	DavidAU
Q5_K_S	5.40 GiB	5,796,295,008	5.774	—	DavidAU
Q5_K_M	5.52 GiB	5,929,988,448	5.908	—	DavidAU
Q2_K2 shards	7.55 GiB	8,106,648,256	8.076	—	DavidAU
Q6_K3 shards	15.12 GiB	16,236,966,592	16.176	—	DavidAU
IQ4_XS3 shards	15.50 GiB	16,642,044,960	16.579	—	DavidAU
Q8_03 shards	25.70 GiB	27,592,324,128	27.488	—	DavidAU

KV cache by context

computed per layer

Context	KV cache (f16)●	Flat formula	Overstated by	Full / windowed / recurrent
4,096	0.50 GiB	0.50 GiB	—	32 / 0 / 0
8,192	1.00 GiB	1.00 GiB	—	32 / 0 / 0
16,384	2.00 GiB	2.00 GiB	—	32 / 0 / 0
32,768	4.00 GiB	4.00 GiB	—	32 / 0 / 0
65,536	8.00 GiB	8.00 GiB	—	32 / 0 / 0
131,072	16.00 GiB	16.00 GiB	—	32 / 0 / 0

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 4.21 GiB. The real file is 4.76 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

128

Hidden size

4096

Vocab

128,256

Sliding window

none

SWA period

—

MLA

Experts

—

Experts per token

—

use_sliding_window

—

Questions people ask

How much VRAM does L3-Dark-Planet-8B need?: Q4_K_M is exactly 5,113,631,072 bytes (4.76 GiB) in weights. Add the KV cache, which depends on your context length, plus roughly half a gigabyte of runtime overhead.
How large is L3-Dark-Planet-8B's KV cache?: 4.00 GiB at 32K context with an f16 cache, computed per layer. Quantizing the cache to q8_0 roughly halves it, which is often the difference between a context length fitting and not.
Which quantization of L3-Dark-Planet-8B 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.