AxForge
Sign in Get started

Model reference · open weights

dialseg-ar-gemma3

LLMs MBZUAI Text gen 1 build Non-commercial 0 dl/mo

dialseg-ar-gemma3 is an open-weight language model from MBZUAI. dialseg-ar-gemma3-4B (BF16) weighs 8.6 GB; the smallest configuration that runs it is RTX 3060 12 GB.

  • DialSeg-Ar-Gemma3 is a 4.3B parameter text-generation model developed by MBZUAI for linear semantic segmentation of dialectal conversational Arabic.
  • It splits sequences of utterances into contiguous topic-coherent segments and is licensed under cc-by-nc-4.0.
  • The model supports Arabic and is designed for applications such as transcript chunking and discourse preprocessing.

Summary of the MBZUAI/dialseg-ar-gemma3-4B model card, 2026-10-01

Hugging Face ↗

What it is

Released byMBZUAI
Released2026-04-15
Parameters4.3B
VRAM8.6 GB for the weights

What it runs on

Memory and cards for dialseg-ar-gemma3-4B (BF16)

8.6 GBweights, file size
762 MBruntime overhead, at least

How much memory each request adds isn't estimated yet for this architecture. The weights need at least the cards below, plus room for the context.

CardWeights alone
RTX 3060 12 GBfits
RTX 4060 Ti 16 GBfits
RTX 3090 24 GBfits
RTX 4090 24 GBfits
RTX 5090 32 GBfits
L40S 48 GBfits
A100 80 GBfits
H100 80 GBfits
RTX PRO 6000 Blackwell 96 GBfits
DGX Spark (GB10) 128 GB unifiedfits
H200 141 GBfits
B200 180 GBfits

How it works

How language models work

Your prompttext / messagesTransformerattention over tokensNext-token loopgenerate + streamResponsetext · tool callsA language model reads your tokens and predicts the next one, again and again, streaming the reply back.
© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms