Nusantara 4b Indo Chat 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 14 quants, from 1.6 GB (Q2_K) to 4.2 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 13.4 GB.
Nusantara 4b Indo Chat – a 3.95B parameter Qwen2 model for Indonesian language tasks
Nusantara 4b Indo Chat is a 3.95B parameter Qwen2 model trained on 32768 context tokens. It is released under the apache-2.0 license and is available in multiple GGUF quantizations.
Good at
- Large context handling
- Indonesian language understanding
- Chat‑style interactions
Limits
- No vision support
- Requires 8k context for memory estimates
- License is apache-2.0
Best for
- Chatbot development
- Indonesian content generation
- Fine‑tuning for local use
Who it’s for. Developers building Indonesian language chat applications or fine‑tuning models for local deployment. The model is suitable for users with access to llama.cpp and a GPU or CPU with sufficient VRAM.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 1.6 GB | 5.5 GB | Fits | Get file → | |
| Q3_K_S | 1.9 GB | 5.7 GB | Fits | Get file → | |
| Q3_K_M | 2.0 GB | 5.9 GB | Fits | Get file → | |
| Q3_K_L | 2.2 GB | 6.0 GB | Fits | Get file → | |
| Q4_0 | 2.3 GB | 6.2 GB | Fits | Get file → | |
| Q4_K_S | 2.3 GB | 6.2 GB | Fits | Get file → | |
| Q4_K_M | 2.5 GB | 6.3 GB | Fits | Get file → | |
| Q4_1 | 2.6 GB | 6.4 GB | Fits | Get file → | |
| Q5_0 | 2.8 GB | 6.6 GB | Fits | Get file → | |
| Q5_K_S | 2.8 GB | 6.6 GB | Fits | Get file → | |
| Q5_K_M | 2.8 GB | 6.7 GB | Fits | Get file → | |
| Q5_1 | 3.0 GB | 6.9 GB | Fits | Get file → | |
| Q6_K | 3.2 GB | 7.1 GB | Fits | Get file → | |
| Q8_0 | 4.2 GB | 8.1 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_0 or Q4_K_S (est. 6.2 GB). For 6 GB VRAM, Q3_K_L or Q4_1 (est. 6 GB). For 4 GB VRAM, Q2_K (est. 5.5 GB) is the smallest option. Estimates are approximate.
What GPU do you need for Nusantara 4b Indo Chat?
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).
- 12 GB VRAM: the best quant that fits is Q8_0 (4.2 GB file, about 8.1 GB in use).
Which Nusantara 4b Indo Chat quant should you choose?
Q4_K_M is the usual starting point for Nusantara 4b Indo Chat: it balances file size and quality well. Here it is a 2.5 GB file.
The Q8_0 file is 4.2 GB, about 1.7 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 1.6 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
Source
Frequently asked questions about Nusantara 4b Indo Chat
How much VRAM does Nusantara 4b Indo Chat 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 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 GGUF?
It depends on the quant: Q2_K is 1.6 GB, Q3_K_S is 1.9 GB, Q3_K_M is 2.0 GB, Q3_K_L is 2.2 GB, Q4_0 is 2.3 GB, Q4_K_S is 2.3 GB and 8 more.
What context length does Nusantara 4b Indo Chat 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 GGUF?
The files are on Hugging Face in the ukung/Nusantara-4b-Indo-Chat-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 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.
Can I run Q4_0 on 8 GB VRAM?
Yes, Q4_0 requires about 6.2 GB of VRAM at 8k context, which fits within 8 GB.
Is this model suitable for Indonesian text generation?
Yes, it is trained for Indonesian language tasks and supports chat interactions.
What license does it use?
The model is released under the apache-2.0 license.