How much VRAM does MiniCPM5-1B need?

Q4_K_M is exactly 688,065,856 bytes (0.64 GiB) in weights. Add the KV cache, which depends on context length, plus roughly half a gigabyte of runtime overhead.

How large is MiniCPM5-1B's KV cache?

0.75 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.

openbmb · text

MiniCPM5-1B

openbmb/MiniCPM5-1B

MiniCPM5-1B at Q4_K_M is exactly 688,065,856 bytes (0.64 GiB / 0.69 GB) — an effective 5.094 bits per weight, not the nominal 4. Its KV cache at 32K is 0.75 GiB.

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

Parameters

1.1B

Architecture

llama

24 layers

Context

131,072

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	0.45 GiB	485,829,952	3.597	—	hudsongouge
Q2_K	0.45 GiB	485,830,240	3.597	—	hudsongouge
Q3_K_M	0.54 GiB	582,899,008	4.315	—	hudsongouge
Q3_K_M	0.54 GiB	582,899,296	4.315	—	hudsongouge
Q4_K_M	0.64 GiB	688,065,856	5.094	—	hudsongouge
Q4_K_M	0.64 GiB	688,065,967	5.094	—	Abiray
Q4_K_M	0.64 GiB	688,066,144	5.094	—	hudsongouge
Q5_K_M	0.73 GiB	786,861,376	5.825	—	hudsongouge
Q5_K_M	0.73 GiB	786,861,664	5.825	—	hudsongouge
Q5_K_M	0.73 GiB	786,862,688	5.825	—	Abiray
Q6_K	0.83 GiB	891,832,928	6.602	—	Abiray
Q8_0	1.07 GiB	1,153,529,152	8.540	—	hudsongouge
Q8_0	1.07 GiB	1,153,529,261	8.540	—	Abiray
Q8_0	1.07 GiB	1,153,529,440	8.540	—	hudsongouge
F16	2.02 GiB	2,166,551,872	16.039	—	hudsongouge
F16	2.02 GiB	2,166,551,980	16.039	—	Abiray
F16	2.02 GiB	2,166,552,160	16.039	—	hudsongouge

KV cache by context

computed per layer

Context	KV cache (f16)●	Flat formula	Overstated by	Full / windowed / recurrent
4,096	0.09 GiB	0.09 GiB	—	24 / 0 / 0
8,192	0.19 GiB	0.19 GiB	—	24 / 0 / 0
16,384	0.38 GiB	0.38 GiB	—	24 / 0 / 0
32,768	0.75 GiB	0.75 GiB	—	24 / 0 / 0
65,536	1.50 GiB	1.50 GiB	—	24 / 0 / 0
131,072	3.00 GiB	3.00 GiB	—	24 / 0 / 0

Compare with

same modality, comparable size

vs Qwen3-4B vs HyperCLOVAX-SEED-Text-Instruct-1.5B vs Llama-3.2-1B-Instruct vs ced-base vs gemma-3-1b-it vs Qwen3-1.7B 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 0.57 GiB. The real file is 0.64 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

1536

Vocab

130,560

Sliding window

none

SWA period

—

MLA

Experts

—

Experts per token

—

use_sliding_window

—

Questions people ask

How much VRAM does MiniCPM5-1B need?: Q4_K_M is exactly 688,065,856 bytes (0.64 GiB) in weights. Add the KV cache, which depends on your context length, plus roughly half a gigabyte of runtime overhead.
How large is MiniCPM5-1B's KV cache?: 0.75 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.
Which quantization of MiniCPM5-1B 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.