IlyaGusev · text

gemma-2-9b-it-abliterated

IlyaGusev/gemma-2-9b-it-abliterated

gemma-2-9b-it-abliterated at Q4_K_M is exactly 5,761,057,760 bytes (5.37 GiB / 5.76 GB) — an effective 4.987 bits per weight, not the nominal 4. Its KV cache at 32K is 5.99 GiB, not the 10.50 GiB a flat formula predicts.

From the file· summed from 1 file(s)From the file· KV per layer
Parameters
9.2B
Architecture
gemma2
42 layers
Context
8,192
native (config.json)
License
gemma

Shipped quantizations

● exact bytes, summed from published files
QuantSize●Exact bytes●Effective bpw●Tensors●Publisher
IQ2_M3.20 GiB3,434,669,0242.973—bartowski
Q2_K3.54 GiB3,805,397,9843.294—bartowski
Q2_K_L3.75 GiB4,027,605,9843.486—bartowski
IQ3_XS3.86 GiB4,144,989,1523.588—bartowski
Q3_K_S4.04 GiB4,337,664,9923.755—bartowski
IQ3_M4.19 GiB4,494,615,5203.891—bartowski
Q3_K_M4.43 GiB4,761,781,2164.122—bartowski
Q3_K_L4.78 GiB5,132,452,8324.443—bartowski
IQ4_XS4.83 GiB5,183,030,2404.487—bartowski
Q4_05.08 GiB5,459,198,9444.726—bartowski
Q4_K_S5.10 GiB5,478,925,2804.743—bartowski
Q4_K_M5.37 GiB5,761,057,7604.987—bartowski
Q4_K_L5.57 GiB5,983,265,7605.179—bartowski
Q5_K_S6.04 GiB6,483,592,1605.612—bartowski
Q5_K_M6.19 GiB6,647,366,6245.754—bartowski
Q5_K_L6.40 GiB6,869,574,6245.947—bartowski
Q6_K7.07 GiB7,589,069,7926.569—bartowski
Q6_K_L7.27 GiB7,811,277,7926.762—bartowski
Q8_09.15 GiB9,827,148,7688.507—bartowski
F3234.43 GiB36,972,880,57632.005—bartowski

KV cache by context

computed per layer — this model uses sliding-window attention
ContextKV cache (f16)●Flat formulaOverstated byFull / windowed / recurrent
4,0961.31 GiB1.31 GiB—21 / 21 / 0
8,1922.05 GiB2.63 GiB1.28×21 / 21 / 0
16,3843.36 GiB5.25 GiB1.56×21 / 21 / 0
32,7685.99 GiB10.50 GiB1.75×21 / 21 / 0
65,53611.24 GiB21.00 GiB1.87×21 / 21 / 0
131,07221.74 GiB42.00 GiB1.93×21 / 21 / 0

21 of 42 layers cache only a 4,096-token window rather than the full context, on a period of 2. Figures assume the default configuration; --swa-full disables the saving entirely.

Compare with

same modality, comparable size
vs Qwen3-Coder-30B-A3B-Instructvs gemma-4-12B-it-qat-q4_0-unquantizedvs gemma-4-E4B-itvs Qwen3-30B-A3B-Thinking-2507vs Qwen3-4Bvs Qwen3-8BAll alternatives →Will it fit on my card? →

Will it run on your card?

full quant x context sweep
By VRAM:8GB12GB16GB24GB32GB48GB
Radeon RX 6500 XT 4GBGeForce RTX 3050 6GBGeForce RTX 5050 8GBGeForce RTX 3080 10GBGeForce RTX 2080 Ti 11GBGeForce RTX 5070 12GBGeForce RTX 5060 Ti 16GBApple M3 Pro 18GBGeForce RTX 3080 Ti 20GBGeForce RTX 5090 D V2 24GBGeForce RTX 5090 D 32GBApple M5 Max 36GBApple M5 Pro 48GBApple M5 Max 64GBApple M3 Ultra 96GBApple M5 Max 128GBApple M2 Ultra 192GBApple M3 Ultra 256GBApple M3 Ultra 512GB

Why other calculators give a different number

A parameters × bits ÷ 8 estimate puts Q4_K_M at roughly 4.84 GiB. The real file is 5.37 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 10.50 GiB at 32K context where the real figure is 5.99 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
16
KV heads
8
Head dim
256
Hidden size
3584
Vocab
256,000
Sliding window
4096
SWA period
2
MLA
no
Experts
—
Experts per token
—
use_sliding_window
—

Questions people ask

How much VRAM does gemma-2-9b-it-abliterated need?
Q4_K_M is exactly 5,761,057,760 bytes (5.37 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-2-9b-it-abliterated's KV cache?
5.99 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-2-9b-it-abliterated 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.