NU

Nusantara 4b Indo Chat i1

NusantaraGGUF by mradermacherUpdated 2024-12-22
Download on Hugging Face
Parameters3.95B
Context32K
Layers40
Architectureqwen2
Smallest quant1.1 GB
Quick answer

Nusantara 4b Indo Chat i1 needs about 6.3 GB of memory at Q4_K_M (a 2.5 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 22 quants, from 1.1 GB (IQ1_S) to 3.2 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 13.4 GB.

Nusantara 4b Indo Chat i1 is a 3.95B-parameter Nusantara model in GGUF format, quantized by mradermacher. Its trained context length is 32K tokens. The repository has 22 quant files, from 1.1 GB (IQ1_S) to 3.2 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S1.1 GB 4.9 GB
Fits Get file →
IQ1_M1.1 GB 5.0 GB
Fits Get file →
IQ2_XXS1.2 GB 5.1 GB
Fits Get file →
IQ2_XS1.3 GB 5.2 GB
Fits Get file →
IQ2_S1.4 GB 5.3 GB
Fits Get file →
Q2_K_S1.5 GB 5.4 GB
Fits Get file →
IQ2_M1.5 GB 5.4 GB
Fits Get file →
Q2_K1.6 GB 5.5 GB
Fits Get file →
IQ3_XXS1.6 GB 5.5 GB
Fits Get file →
IQ3_XS1.8 GB 5.6 GB
Fits Get file →
IQ3_S1.9 GB 5.7 GB
Fits Get file →
Q3_K_S1.9 GB 5.7 GB
Fits Get file →
IQ3_M1.9 GB 5.8 GB
Fits Get file →
Q3_K_M2.0 GB 5.9 GB
Fits Get file →
Q3_K_L2.2 GB 6.0 GB
Fits Get file →
IQ4_XS2.2 GB 6.1 GB
Fits Get file →
Q4_02.3 GB 6.2 GB
Fits Get file →
Q4_K_S2.3 GB 6.2 GB
Fits Get file →
Q4_K_M2.5 GB 6.3 GB
Fits Get file →
Q5_K_S2.8 GB 6.6 GB
Fits Get file →
Q5_K_M2.8 GB 6.7 GB
Fits Get file →
Q6_K3.2 GB 7.1 GB
Fits Get file →

What GPU do you need for Nusantara 4b Indo Chat i1?

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: the best quant that fits is Q3_K_L (2.2 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q6_K (3.2 GB file, about 7.1 GB in use).

Which Nusantara 4b Indo Chat i1 quant should you choose?

Q4_K_M is the usual starting point for Nusantara 4b Indo Chat i1: it balances file size and quality well. Here it is a 2.5 GB file.

If memory is tight, the smallest file is IQ1_S at 1.1 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

Architectureqwen2
Parameters3.95B
Layers40
Trained context32,768 tokens
KV cache (fp16)400 KB per token

Source

Quantized bymradermacher
FamilyNusantara
Licenseapache-2.0
Downloads (HF)226
Last updated2024-12-22

Frequently asked questions about Nusantara 4b Indo Chat i1

How much VRAM does Nusantara 4b Indo Chat i1 need?

About 6.3 GB at Q4_K_M with an 8K context window. That is the 2.5 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 Nusantara 4b Indo Chat i1 on an 8 GB GPU?

Yes, with Q6_K: the 3.2 GB file needs about 7.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Nusantara 4b Indo Chat i1 GGUF?

It depends on the quant: IQ1_S is 1.1 GB, IQ1_M is 1.1 GB, IQ2_XXS is 1.2 GB, IQ2_XS is 1.3 GB, IQ2_S is 1.4 GB, Q2_K_S is 1.5 GB and 16 more.

What context length does Nusantara 4b Indo Chat i1 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 3.4 GB at 8K and 13.4 GB at 32K.

Where can I download Nusantara 4b Indo Chat i1 GGUF?

The files are on Hugging Face in the mradermacher/Nusantara-4b-Indo-Chat-i1-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 Nusantara 4b Indo Chat i1 use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Other GGUFs of Nusantara-4b-Indo-Chat

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Nusantara models

All Nusantara →

Other small models

All small models →