openbmb · audio tts

VoxCPM2

openbmb/VoxCPM2

VoxCPM2 at Q4_K is exactly 1,689,498,432 bytes (1.57 GiB / 1.69 GB) — an effective 5.902 bits per weight, not the nominal 4.

From the file· summed from 1 file(s)From the file· KV per layer
Parameters
2.3B
Architecture
voxcpm-acoustic
null layers
Context
native (config.json)
License
apache-2.0

Shipped quantizations

exact bytes, summed from published files
QuantSizeExact bytesEffective bpwTensorsPublisher
Q4_K1.57 GiB1,689,498,4325.902cstr
Q8_01.61 GiB1,727,309,9206.034wt5719001
Q8_01.61 GiB1,727,309,9206.034DennisHuang648
Q8_02.63 GiB2,827,049,7929.876cstr
F164.63 GiB4,972,550,20817.371cstr
F162 shards4.72 GiB5,073,076,89617.723wt5719001
F162 shards4.72 GiB5,073,076,89617.723DennisHuang648

Compare with

same modality, comparable size

Will it run on your card?

full quant x context sweep

Why other calculators give a different number

A parameters × bits ÷ 8 estimate puts Q4_K at roughly 1.20 GiB. The real file is 1.57 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
Hidden size
Vocab
Sliding window
none
SWA period
MLA
no
Experts
Experts per token
use_sliding_window

Questions people ask

How much VRAM does VoxCPM2 need?
Q4_K is exactly 1,689,498,432 bytes (1.57 GiB) in weights. Add the KV cache, which depends on your context length, plus roughly half a gigabyte of runtime overhead.
Which quantization of VoxCPM2 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.