How much VRAM does Minimax-M3-abliterated-clean need?

Q2_K is exactly 155,014,798,336 bytes (144.37 GiB) in weights. Add the KV cache, which depends on context length, plus roughly half a gigabyte of runtime overhead.

How large is Minimax-M3-abliterated-clean's KV cache?

3.75 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 Minimax-M3-abliterated-clean a mixture-of-experts model?

Yes — 128 experts with 4 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.

OpenYourMind · vision language · mixture of experts

Minimax-M3-abliterated-clean

OpenYourMind/Minimax-M3-abliterated-clean

Minimax-M3-abliterated-clean at Q2_K is exactly 155,014,798,336 bytes (144.37 GiB / 155.01 GB) — an effective 2.904 bits per weight, not the nominal 2. Its KV cache at 32K is 3.75 GiB.

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

Parameters

427B

total, not active

Architecture

minimax-m3

60 layers

Context

1,048,576

native (config.json)

License

other

Shipped quantizations

● exact bytes, summed from published files

Quant	Size●	Exact bytes●	Effective bpw●	Tensors●	Publisher
Q2_K	144.37 GiB	155,014,798,336	2.904	—	Sica-Quants-2
Q3_K_S	171.06 GiB	183,676,797,952	3.441	—	Sica-Quants-2

KV cache by context

computed per layer

Context	KV cache (f16)●	Flat formula	Overstated by	Full / windowed / recurrent
4,096	0.47 GiB	0.47 GiB	—	60 / 0 / 0
8,192	0.94 GiB	0.94 GiB	—	60 / 0 / 0
16,384	1.88 GiB	1.88 GiB	—	60 / 0 / 0
32,768	3.75 GiB	3.75 GiB	—	60 / 0 / 0
65,536	7.50 GiB	7.50 GiB	—	60 / 0 / 0
131,072	15.00 GiB	15.00 GiB	—	60 / 0 / 0

Compare with

same modality, comparable size

vs Qwen3.6-35B-A3B vs Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP vs Qwen3.5-122B-A10B vs Qwopus3.6-35B-A3B-v1 vs Qwen3.5-35B-A3B vs Kimi-K2.7-Code All alternatives →Will it fit on my card? →

Why other calculators give a different number

A parameters × bits ÷ 8 estimate puts Q2_K at roughly 223.71 GiB. The real file is 144.37 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

6144

Vocab

200,064

Sliding window

none

SWA period

—

MLA

Experts

128

Experts per token

use_sliding_window

—

Questions people ask

How much VRAM does Minimax-M3-abliterated-clean need?: Q2_K is exactly 155,014,798,336 bytes (144.37 GiB) in weights. Add the KV cache, which depends on your context length, plus roughly half a gigabyte of runtime overhead.
How large is Minimax-M3-abliterated-clean's KV cache?: 3.75 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 Minimax-M3-abliterated-clean a mixture-of-experts model?: Yes — 128 experts, 4 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 Minimax-M3-abliterated-clean 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.