rpDungeon · text

Gemma-4-E4B-Luchador

rpDungeon/Gemma-4-E4B-Luchador

Gemma-4-E4B-Luchador at Q4_K_M is exactly 5,405,168,288 bytes (5.03 GiB / 5.41 GB) — an effective 5.408 bits per weight, not the nominal 4. Its KV cache at 32K is 0.51 GiB, not the 2.63 GiB a flat formula predicts.

From the file· summed from 1 file(s)From the file· KV per layer
Parameters
8.0B
Architecture
gemma4
42 layers
Context
131,072
native (config.json)
License
gemma

Shipped quantizations

exact bytes, summed from published files
QuantSizeExact bytesEffective bpwTensorsPublisher
IQ2_M3.69 GiB3,959,906,9763.962bartowski
Q2_K4.15 GiB4,458,091,1684.460bartowski
IQ3_XS4.31 GiB4,632,038,0484.634bartowski
Q3_K_S4.38 GiB4,699,693,7284.702bartowski
IQ3_M4.44 GiB4,767,779,4884.770bartowski
Q3_K_M4.56 GiB4,898,728,6084.901bartowski
Q3_K_L4.69 GiB5,034,224,2885.037bartowski
IQ4_XS4.76 GiB5,112,826,5285.115bartowski
Q4_04.87 GiB5,223,858,8485.226bartowski
IQ4_NL4.87 GiB5,232,224,9285.235bartowski
Q4_K_S4.88 GiB5,235,655,3285.238bartowski
Q2_K_L4.94 GiB5,303,243,4245.306bartowski
Q4_K_M5.03 GiB5,405,168,2885.408bartowski
Q4_15.08 GiB5,458,477,7285.461bartowski
Q5_K_S5.31 GiB5,701,288,6085.704bartowski
Q5_K_M5.42 GiB5,820,881,5685.824bartowski
Q4_K_L5.82 GiB6,250,320,5446.253bartowski
Q6_K5.90 GiB6,329,952,9286.333bartowski
Q5_K_L6.21 GiB6,666,033,8246.669bartowski
Q6_K_L6.68 GiB7,175,105,1847.179bartowski
Q8_07.48 GiB8,031,240,8648.035bartowski
BF1614.02 GiB15,053,095,26415.060bartowski

KV cache by context

computed per layer — this model uses sliding-window attention
ContextKV cache (f16)Flat formulaOverstated byFull / windowed / recurrent
4,0960.12 GiB0.33 GiB2.67×7 / 35 / 0
8,1920.18 GiB0.66 GiB3.69×7 / 35 / 0
16,3840.29 GiB1.31 GiB4.57×7 / 35 / 0
32,7680.51 GiB2.63 GiB5.19×7 / 35 / 0
65,5360.94 GiB5.25 GiB5.57×7 / 35 / 0
131,0721.82 GiB10.50 GiB5.77×7 / 35 / 0

35 of 42 layers cache only a 512-token window rather than the full context, on a period of . Figures assume the default configuration; --swa-full disables the saving entirely.

Compare with

same modality, comparable size

Will it run on your card?

full quant x context sweep

Why other calculators give a different number

A parameters × bits ÷ 8 estimate puts Q4_K_M at roughly 4.19 GiB. The real file is 5.03 GiB, because a quantization is a mixture and some tensors are always kept at higher precision. The larger discrepancy is the cache: a flat formula gives 2.63 GiB at 32K context where the real figure is 0.51 GiB, because most of this model's layers cache a fixed window rather than the whole context.

Architecture

from config.json
Layers
42
Attention heads
8
KV heads
2
Head dim
256
Hidden size
2560
Vocab
262,144
Sliding window
512
SWA period
MLA
no
Experts
Experts per token
use_sliding_window

Questions people ask

How much VRAM does Gemma-4-E4B-Luchador need?
Q4_K_M is exactly 5,405,168,288 bytes (5.03 GiB) in weights. Add the KV cache, which depends on your context length, plus roughly half a gigabyte of runtime overhead.
How large is Gemma-4-E4B-Luchador's KV cache?
0.51 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 Gemma-4-E4B-Luchador 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.