OpenModelsHQ

Voxtral-Mini-4B-Realtime-2602

Mistral AISpeechDenseApache-2.0

Voxtral-Mini-4B-Realtime-2602 is an open-weight speech to text model from Mistral AI with 4.4B parameters. At 4-bit it needs about 3.9 GB of memory, so the smallest current device that fits it is the Mac mini M6 (16GB).

Overview

Estimated memory at 4-bit
3.9GB

Estimated memory for the weights at 4-bit (plus runtime overhead). Image, video and speech models also need working memory that depends on resolution or clip length.

Total parameters
4.4B
Dense
Type
Speech to text
Released 21 Jan 2026
Cheapest API, blended / 1M
No hosted API
Weights only

Key information

Lab
Mistral AI
Released
21 Jan 2026
Parameters
4.4B
Type
Speech to text
License
Apache-2.0
HF downloads, 30 days
1,511,441
View all

Will it run on your hardware?

How we estimate
Memory needed vs devices
Voxtral-Mini-4B-Realtime-2602 needs about 3.9 GB at 4-bit, 6.1 GB at 8-bit and 10.7 GB at 16-bit. At 4-bit it fits GeForce RTX 5060 Ti 16GB, GeForce RTX 5090, DGX Spark, Mac Studio M5 Ultra (256GB). Dashed lines are usable memory on each device; a model fits when its estimate stays within 90% of it. Log scale. 8k context.
Memory needed vs devices: data
Estimate or deviceMemory
Q43.9 GB
Q86.1 GB
BF1610.7 GB
RTX 5060 Ti 16 GB16 GB usable
RTX 5090 32 GB32 GB usable
DGX Spark 128 GB108.8 GB usable
Mac Studio M5 Ultra 256 GB192 GB usable

Single-device memory estimate. Pick a device to update the On your device column.

36 GB usable memory

FormatMemory neededOn your deviceExample hardware
4-bit (Q4)≈ 3.9 GBFits 11%Mac mini M6 (16GB)16 GB memory
8-bit (Q8)≈ 6.1 GBFits 17%Mac mini M6 (16GB)16 GB memory
16-bit (BF16)≈ 10.7 GBFits 30%GeForce RTX 5060 Ti 16GB16 GB memory

Fits means the estimate stays within 90% of usable memory. Tight is above 90% and up to 100%. Too big is above 100%. These are memory checks, not speed or compatibility tests.

Mac allowances are 66% of total RAM up to 36 GB, and 75% above. AI boxes allow 85% because their memory is shared with the operating system.

Where to run it

On a Mac

Start with the MLX files, built for Apple Silicon.

mlx-community/Voxtral-Mini-4B-Realtime-2602-4bitCheck your Mac

With GGUF

GGUF build for compatible runtimes (for example ComfyUI GGUF nodes).

ggml-org/Voxtral-Mini-4B-Realtime-2602-GGUFFind compatible hardware

Through an API

No hosted API found.

More about this model

Frequently asked questions

How much memory does Voxtral-Mini-4B-Realtime-2602 need? About 3.9 GB at 4-bit, 6.1 GB at 8-bit and 10.7 GB at 16-bit (BF16), for the weights plus runtime overhead.

Can I run Voxtral-Mini-4B-Realtime-2602 on a Mac? The smallest current Mac that fits the 4-bit estimate of 3.9 GB is the Mac mini M6 (16GB). An MLX build is available: mlx-community/Voxtral-Mini-4B-Realtime-2602-4bit.

What does it need to run? The weights need about 3.9 GB at 4-bit and 10.7 GB at 16-bit. Image, video and speech models also need working memory that depends on resolution or clip length, so leave extra room. MLX build: mlx-community/Voxtral-Mini-4B-Realtime-2602-4bit. GGUF build: ggml-org/Voxtral-Mini-4B-Realtime-2602-GGUF.

What does it cost through an API? We did not find a hosted API for this model.

License in plain English

Apache-2.0. This license permits commercial use, modification and redistribution, with conditions such as keeping the required notices. This summary is not legal advice.

Read Apache-2.0

Read about this license

OMHQ RigBench

Not yet tested. We show no speed or quality score without a measurement.

Revision history and sources

Last updated . Sources:Hugging Face model card, MLX repository, GGUF repository.