How much VRAM does Baichuan-M2-32B-abliterated need?

Q4_K_M is exactly 19,851,337,920 bytes (18.49 GiB) in weights. Add the KV cache, which depends on context length, plus roughly half a gigabyte of runtime overhead.

How large is Baichuan-M2-32B-abliterated's KV cache?

8.00 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.

nicoboss · text

Baichuan-M2-32B-abliterated

nicoboss/Baichuan-M2-32B-abliterated

Baichuan-M2-32B-abliterated at Q4_K_M is exactly 19,851,337,920 bytes (18.49 GiB / 19.85 GB) — an effective 4.847 bits per weight, not the nominal 4. Its KV cache at 32K is 8.00 GiB.

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

Parameters

32.8B

Architecture

qwen2

64 layers

Context

131,072

native (config.json)

License

—

Shipped quantizations

● exact bytes, summed from published files

Quant	Size●	Exact bytes●	Effective bpw●	Tensors●	Publisher
Q2_K	11.47 GiB	12,313,100,480	3.006	—	mradermacher
Q3_K_S	13.40 GiB	14,392,332,480	3.514	—	mradermacher
Q3_K_M	14.84 GiB	15,935,049,920	3.891	—	mradermacher
Q3_K_L	16.06 GiB	17,247,080,640	4.211	—	mradermacher
IQ4_XS	16.64 GiB	17,870,102,720	4.363	—	mradermacher
Q4_K_S	17.49 GiB	18,784,411,840	4.587	—	mradermacher
Q4_K_M	18.49 GiB	19,851,337,920	4.847	—	mradermacher
Q5_K_S	21.08 GiB	22,638,256,320	5.528	—	mradermacher
Q5_K_M	21.66 GiB	23,262,159,040	5.680	—	mradermacher
Q6_K	25.04 GiB	26,886,156,480	6.565	—	mradermacher
Q8_0	32.43 GiB	34,820,886,720	8.502	—	mradermacher

KV cache by context

computed per layer

Context	KV cache (f16)●	Flat formula	Overstated by	Full / windowed / recurrent
4,096	1.00 GiB	1.00 GiB	—	64 / 0 / 0
8,192	2.00 GiB	2.00 GiB	—	64 / 0 / 0
16,384	4.00 GiB	4.00 GiB	—	64 / 0 / 0
32,768	8.00 GiB	8.00 GiB	—	64 / 0 / 0
65,536	16.00 GiB	16.00 GiB	—	64 / 0 / 0
131,072	32.00 GiB	32.00 GiB	—	64 / 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 17.16 GiB. The real file is 18.49 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

5120

Vocab

152,064

Sliding window

none

SWA period

—

MLA

Experts

—

Experts per token

—

use_sliding_window

false

Questions people ask

How much VRAM does Baichuan-M2-32B-abliterated need?: Q4_K_M is exactly 19,851,337,920 bytes (18.49 GiB) in weights. Add the KV cache, which depends on your context length, plus roughly half a gigabyte of runtime overhead.
How large is Baichuan-M2-32B-abliterated's KV cache?: 8.00 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 Baichuan-M2-32B-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.