GN

gnani evon v3.3 30B A3B

GnaniGGUF by luminenioUpdated 2026-09-07
Download on Hugging Face
Parameters31.7B
Context1024K
Layers52
Architecturenemotron_h_moe
Smallest quant18.1 GB
Quick answer

gnani evon v3.3 30B A3B needs about 32.1 GB of memory at Q4_K_M (a 24.7 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 11 quants, from 18.1 GB (Q2_K) to 33.8 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 27.9 GB.

Gnani Evon v3.3 30B A3B – large‑scale Indic language model

Gnani Evon v3.3 30B A3B is a 31.7B parameter hybrid Mamba‑Transformer Mixture of Experts model. It supports 128K context and is trained for deep reasoning and tool usage in Indic languages and English.

Good at

  • Indic language reasoning
  • Tool calling
  • Long‑context RAG

Limits

  • No vision support
  • Requires large VRAM for full precision
  • License is other

Best for

  • Chat assistants in Hindi, Bengali, Tamil
  • Multilingual RAG with 128K context
  • AI agents with tool usage

Who it’s for. Developers building multilingual chat or RAG systems that need strong Indic language understanding and reasoning. The model is suitable for applications that can allocate sufficient GPU memory for a 30B MoE model.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K18.1 GB 25.5 GB
Too big Get file →
Q3_K_S18.1 GB 25.6 GB
Too big Get file →
IQ4_XS18.4 GB 25.8 GB
Too big Get file →
Q3_K_M20.0 GB 27.5 GB
Too big Get file →
Q3_K_L20.9 GB 28.4 GB
Too big Get file →
Q4_K_S22.1 GB 29.6 GB
Too big Get file →
Q5_K_S24.0 GB 31.4 GB
Too big Get file →
Q4_K_M24.7 GB 32.1 GB
Too big Get file →
Q5_K_M26.2 GB 33.7 GB
Too big Get file →
Q6_K33.7 GB 41.2 GB
Too big Get file →
Q8_033.8 GB 41.3 GB
Too big Get file →

For 8‑GB VRAM, use Q2_K or Q3_K_S (18 GB file, ~25.5 GB memory at 8K context). For 16‑GB VRAM, Q4_K_S or Q5_K_S (22–24 GB file, ~29–31 GB memory). For 32‑GB VRAM, Q4_K_M or Q5_K_M (24–26 GB file, ~32–34 GB memory).

What GPU do you need for gnani evon v3.3 30B A3B?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 32 GB VRAM: the best quant that fits is Q5_K_S (24.0 GB file, about 31.4 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (33.8 GB file, about 41.3 GB in use).

Which gnani evon v3.3 30B A3B quant should you choose?

Q4_K_M is the usual starting point for gnani evon v3.3 30B A3B: it balances file size and quality well. Here it is a 24.7 GB file.

The Q8_0 file is 33.8 GB, about 1.4 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q2_K at 18.1 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturenemotron_h_moe
Parameters31.7B (approximate, mixture of experts)
Active parameters3B
Layers52
Trained context1,048,576 tokens
KV cache (fp16)832 KB per token

Source

Quantized byluminenio
FamilyGnani
Licenseother
Downloads (HF)981
Last updated2026-09-07

Frequently asked questions about gnani evon v3.3 30B A3B

How much VRAM does gnani evon v3.3 30B A3B need?

About 32.1 GB at Q4_K_M with an 8K context window. That is the 24.7 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run gnani evon v3.3 30B A3B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 25.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of gnani evon v3.3 30B A3B GGUF?

It depends on the quant: Q2_K is 18.1 GB, Q3_K_S is 18.1 GB, IQ4_XS is 18.4 GB, Q3_K_M is 20.0 GB, Q3_K_L is 20.9 GB, Q4_K_S is 22.1 GB and 5 more.

What context length does gnani evon v3.3 30B A3B support?

The GGUF header lists a trained context length of 1,048,576 tokens (1024K). The KV cache grows with the context you use: about 7.0 GB at 8K and 27.9 GB at 32K.

Where can I download gnani evon v3.3 30B A3B GGUF?

The files are on Hugging Face in the luminenio/gnani-evon-v3.3-30B-A3B-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does gnani evon v3.3 30B A3B use?

Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run this model on 8 GB VRAM?

Use the Q2_K or Q3_K_S quantization; the file is 18 GB and requires about 25.5 GB of VRAM at 8K context.

Does the model support image input?

No, the model has no vision capability.

What is the maximum context length?

The model supports 128K tokens (131,072 tokens).

Similar models

Browse all →

Other medium models

All medium models →