microsoft · text

VibeVoice-ASR

microsoft/VibeVoice-ASR

VibeVoice-ASR at Q4_K is exactly 4,811,829,376 bytes (4.48 GiB / 4.81 GB) — an effective 4.438 bits per weight, not the nominal 4.

From the file· summed from 1 file(s)From the file· KV per layer
Parameters
8.7B
Architecture
vibevoice-tokenizer
null layers
Context
—
native (config.json)
License
mit

Shipped quantizations

● exact bytes, summed from published files
QuantSize●Exact bytes●Effective bpw●Tensors●Publisher
Q4_K4.48 GiB4,811,829,3764.438—cstr
Q8_08.80 GiB9,445,577,0888.712—cstr
Q4_K9.68 GiB10,392,063,2969.585—mudler
Q8_02 shards14.55 GiB15,627,038,33614.413—mudler
F1615.52 GiB16,664,915,26415.370—cstr

Compare with

same modality, comparable size
vs Qwen3-Coder-30B-A3B-Instructvs Qwen3.6-27Bvs Qwen3.8-27Bvs gemma-4-12B-it-qat-q4_0-unquantizedvs gemma-4-E4B-itvs Qwen3-30B-A3B-Thinking-2507All alternatives →Will it fit on my card? →

Will it run on your card?

full quant x context sweep
By VRAM:8GB12GB16GB24GB32GB48GB
Radeon RX 6500 XT 4GBGeForce RTX 3050 6GBGeForce RTX 5050 8GBGeForce RTX 3080 10GBGeForce RTX 2080 Ti 11GBGeForce RTX 5070 12GBGeForce RTX 5060 Ti 16GBApple M3 Pro 18GBGeForce RTX 3080 Ti 20GBGeForce RTX 5090 D V2 24GBGeForce RTX 5090 D 32GBApple M5 Max 36GBApple M5 Pro 48GBApple M5 Max 64GBApple M3 Ultra 96GBApple M5 Max 128GBApple M2 Ultra 192GBApple M3 Ultra 256GBApple M3 Ultra 512GB

Why other calculators give a different number

A parameters × bits ÷ 8 estimate puts Q4_K at roughly 4.54 GiB. The real file is 4.48 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 VibeVoice-ASR need?
Q4_K is exactly 4,811,829,376 bytes (4.48 GiB) in weights. Add the KV cache, which depends on your context length, plus roughly half a gigabyte of runtime overhead.
Which quantization of VibeVoice-ASR 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.