openai · audio asr

whisper-small.en

openai/whisper-small.en

whisper-small.en at Q4_K_M is exactly 171,553,856 bytes (0.16 GiB / 0.17 GB) — an effective 5.677 bits per weight, not the nominal 4.

From the file· summed from 1 file(s)From the file· KV per layer
Parameters
242M
Architecture
whisper
12 layers
Context
—
native (config.json)
License
apache-2.0

Shipped quantizations

● exact bytes, summed from published files
QuantSize●Exact bytes●Effective bpw●Tensors●Publisher
Q4_K_M0.16 GiB171,553,8565.677—handy-computer
Q5_K_M0.18 GiB193,672,2566.409—handy-computer
Q6_K0.20 GiB212,030,5287.017—handy-computer
Q8_00.25 GiB269,674,1448.925—handy-computer
F160.46 GiB492,810,78416.309—handy-computer
F320.90 GiB968,835,61632.063—handy-computer

Compare with

same modality, comparable size
vs nemotron-3.5-asr-streaming-0.6bvs parakeet-tdt-0.6b-v3vs whisper-mediumvs canary-180m-flashvs whisper-large-v3-turbovs parakeet-tdt-0.6b-v2All 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_M at roughly 0.13 GiB. The real file is 0.16 GiB, because a quantization is a mixture and some tensors are always kept at higher precision.

Architecture

from config.json
Layers
12
Attention heads
—
KV heads
—
Head dim
—
Hidden size
—
Vocab
51,864
Sliding window
none
SWA period
—
MLA
no
Experts
—
Experts per token
—
use_sliding_window
—

Questions people ask

How much VRAM does whisper-small.en need?
Q4_K_M is exactly 171,553,856 bytes (0.16 GiB) in weights. Add the KV cache, which depends on your context length, plus roughly half a gigabyte of runtime overhead.
Which quantization of whisper-small.en 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.