How much VRAM does Qwen3-30B-A3B-abliterated need?

Q4_K_M is exactly 18,556,686,304 bytes (17.28 GiB) in weights. Add the KV cache, which depends on context length, plus roughly half a gigabyte of runtime overhead.

How large is Qwen3-30B-A3B-abliterated's KV cache?

3.00 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.

Is Qwen3-30B-A3B-abliterated a mixture-of-experts model?

Yes — 128 experts with 8 routed per token. Every expert must be resident in memory, but only the routed ones are read per token, so its memory requirement and its speed behave very differently.

mlabonne · text · mixture of experts

Qwen3-30B-A3B-abliterated

mlabonne/Qwen3-30B-A3B-abliterated

Qwen3-30B-A3B-abliterated at Q4_K_M is exactly 18,556,686,304 bytes (17.28 GiB / 18.56 GB) — an effective 4.862 bits per weight, not the nominal 4. Its KV cache at 32K is 3.00 GiB.

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

Parameters

30.5B

total, not active

Architecture

qwen3moe

48 layers

Context

40,960

native (config.json)

License

apache-2.0

Shipped quantizations

● exact bytes, summed from published files

Quant	Size●	Exact bytes●	Effective bpw●	Tensors●	Publisher
Q2_K	10.49 GiB	11,258,609,632	2.950	—	mradermacher
Q3_K_S	12.38 GiB	13,292,468,192	3.483	—	mradermacher
Q3_K_M	13.70 GiB	14,711,846,880	3.855	—	mradermacher
Q3_K_L	14.81 GiB	15,900,669,920	4.166	—	mradermacher
IQ4_XS	15.42 GiB	16,557,092,832	4.338	—	mradermacher
Q4_K_S	16.26 GiB	17,456,009,184	4.574	—	mradermacher
Q4_K_M	17.28 GiB	18,556,686,304	4.862	—	mradermacher
Q5_K_S	19.63 GiB	21,080,510,432	5.524	—	mradermacher
Q5_K_M	20.23 GiB	21,725,581,280	5.692	—	mradermacher
Q6_K	23.37 GiB	25,092,532,192	6.575	—	mradermacher
Q8_0	30.25 GiB	32,483,932,128	8.511	—	mradermacher

KV cache by context

computed per layer

Context	KV cache (f16)●	Flat formula	Overstated by	Full / windowed / recurrent
4,096	0.38 GiB	0.38 GiB	—	48 / 0 / 0
8,192	0.75 GiB	0.75 GiB	—	48 / 0 / 0
16,384	1.50 GiB	1.50 GiB	—	48 / 0 / 0
32,768	3.00 GiB	3.00 GiB	—	48 / 0 / 0
65,536	6.00 GiB	6.00 GiB	—	48 / 0 / 0
131,072	12.00 GiB	12.00 GiB	—	48 / 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 15.99 GiB. The real file is 17.28 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

2048

Vocab

151,936

Sliding window

none

SWA period

—

MLA

Experts

128

Experts per token

use_sliding_window

false

Questions people ask

How much VRAM does Qwen3-30B-A3B-abliterated need?: Q4_K_M is exactly 18,556,686,304 bytes (17.28 GiB) in weights. Add the KV cache, which depends on your context length, plus roughly half a gigabyte of runtime overhead.
How large is Qwen3-30B-A3B-abliterated's KV cache?: 3.00 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.
Is Qwen3-30B-A3B-abliterated a mixture-of-experts model?: Yes — 128 experts, 8 routed per token. Every expert must be resident, but only the routed ones are read per token, which is why its memory requirement and its speed behave very differently.
Which quantization of Qwen3-30B-A3B-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.