AxForge
Sign in Get started

Model reference · open weights

gnani-evon

LLMs gnani Text gen · MoE 1 build Open weights 701 dl/mo

gnani-evon is an open-weight language model from gnani. gnani-evon-v3.3-30B-A3B (BF16) weighs 63.5 GB; the smallest configuration that runs it is H100 80 GB.

  • gnani-evon-v3.3 is a 31.7B parameter hybrid Mamba architecture Mixture of Experts model developed by gnani for text generation.
  • It supports a 128K context length and is designed for instruction following, reasoning, and agentic tasks across English and ten Indic languages.
  • The model is released under the apache-2.0 licence.

Summary of the gnani/gnani-evon-v3.3-30B-A3B model card, 2026-10-01

Hugging Face ↗

What it is

Released bygnani
Released2026-08-10
Parameters31.7B
VRAM63.5 GB for the weights

What it runs on

Memory and cards for gnani-evon-v3.3-30B-A3B (BF16)

63.5 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 GB … L40S 48 GB
6 smaller cards		does not fit
A100 80 GBfits
H100 80 GBtight
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