Voxtral models

1 Voxtral model from Mistral AI on Hugging Face, from 4.4B to 4.4B parameters, published by Mistral AI in BF16, with a 128K-token context. The smallest official model, Voxtral-Mini-4B-Realtime-2602, needs about 9.9 GB of VRAM at its published precision; the cheapest live fit is RTX 3060 at $0.110/hr.

Part of the Mistral series

Pick a size

One row per official Voxtral size: the VRAM it needs at each precision, the cheapest GPU that holds it today, and the KV cache for a 32K-token context.

ModelParametersNative VRAMFP8 VRAMINT4 VRAMLive GPU fit (native)Est. $/hrKV cache at 32K
Voxtral-Mini-4B-Realtime-26024.4B9.9 GB5.0 GB2.5 GBRTX 3060$0.110/hrnot published for this architecture

VRAM is weights times a flat 1.2 overhead; the KV cache is a separate per-model figure at 16-bit, shown where the architecture is published. See the methodology.

Official models (1)

ModelParametersPublished asVRAM neededLive GPU fitEst. $/hr
Voxtral-Mini-4B-Realtime-26024.4BBF169.9 GBRTX 3060$0.110/hr

VRAM is for the precision the model is published in: the weights times a flat 1.2 overhead, with the KV cache not included. See the methodology. The fit shown is the lowest-priced single GPU type that holds the model at that precision, or the lowest-priced multi-GPU set (up to 8) when none does.

More from Mistral AI

Start ComfyUI on a rented GPU.

© 2026 Aquanode. All rights reserved.

All trademarks, logos and brand names are the property of their respective owners.