Cendol Llama2 13b Merged needs about 15.1 GB of memory at Q4_K_M (a 7.9 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 22 quants, from 4.9 GB (Q2_K) to 13.8 GB (Q8_0).
13B Indonesian LLaMA‑2 chat model
Cendol Llama2 13b Merged is a 13‑billion‑parameter LLaMA‑2 chat model fine‑tuned for Indonesian languages. It supports a 4096‑token context window and is released under the Apache‑2.0 license.
Good at
- Indonesian language generation
- Chat‑style interactions
- Instruction following
Limits
- No vision support
- Requires 8‑k context for memory estimates
- License is Apache‑2.0
Best for
- Building Indonesian chatbots
- Generating Indonesian text
- Fine‑tuning on Indonesian data
Who it’s for. Developers and researchers needing a large Indonesian language model for chat or text generation. The model is suitable for applications that can run on GPUs with sufficient VRAM and support llama.cpp inference.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 4.9 GB | 8.7 GB | Too big | Get file → | |
| IQ3_XS | 5.4 GB | 9.2 GB | Too big | Get file → | |
| IQ3_S | 5.7 GB | 9.5 GB | Too big | Get file → | |
| Q3_K_S | 5.7 GB | 9.5 GB | Too big | Get file → | |
| IQ3_M | 6.0 GB | 9.8 GB | Too big | Get file → | |
| Q3_K | 6.3 GB | 10.2 GB | Too big | Get file → | |
| Q3_K_M | 6.3 GB | 10.2 GB | Too big | Get file → | |
| Q3_K_L | 6.9 GB | 10.8 GB | Too big | Get file → | |
| IQ4_XS | 7.0 GB | 10.9 GB | Too big | Get file → | |
| Q4_0 | 7.4 GB | 11.2 GB | Too big | Get file → | |
| IQ4_NL | 7.4 GB | 11.3 GB | Too big | Get file → | |
| Q4_K_S | 7.4 GB | 11.3 GB | Too big | Get file → | |
| Q4_K | 7.9 GB | 11.7 GB | Too big | Get file → | |
| Q4_K_M | 7.9 GB | 11.7 GB | Too big | Get file → | |
| Q4_1 | 8.2 GB | 12.0 GB | Too big | Get file → | |
| Q5_0 | 9.0 GB | 12.8 GB | Too big | Get file → | |
| Q5_K_S | 9.0 GB | 12.8 GB | Too big | Get file → | |
| Q5_K | 9.2 GB | 13.1 GB | Too big | Get file → | |
| Q5_K_M | 9.2 GB | 13.1 GB | Too big | Get file → | |
| Q5_1 | 9.8 GB | 13.6 GB | Too big | Get file → | |
| Q6_K | 10.7 GB | 14.5 GB | Too big | Get file → | |
| Q8_0 | 13.8 GB | 17.7 GB | Too big | Get file → |
For 8‑GB VRAM, use Q4_K_M (7.87 GB file, ~15.1 GB memory at 8k context). For 12‑GB VRAM, Q5_K_M (9.23 GB file, ~16.4 GB memory). For 16‑GB VRAM, Q6_K (10.68 GB file, ~17.9 GB memory). Estimates are approximate.
What GPU do you need for Cendol Llama2 13b Merged?
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: the best quant that fits is Q4_1 (8.2 GB file, about 15.4 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (13.8 GB file, about 21.0 GB in use).
Which Cendol Llama2 13b Merged quant should you choose?
Q4_K_M is the usual starting point for Cendol Llama2 13b Merged: it balances file size and quality well. Here it is a 7.9 GB file.
The Q8_0 file is 13.8 GB, about 1.8 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 4.9 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
Frequently asked questions about Cendol Llama2 13b Merged
How much VRAM does Cendol Llama2 13b Merged need?
About 15.1 GB at Q4_K_M with an 8K context window. That is the 7.9 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 Cendol Llama2 13b Merged on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 12.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Cendol Llama2 13b Merged GGUF?
It depends on the quant: Q2_K is 4.9 GB, IQ3_XS is 5.4 GB, IQ3_S is 5.7 GB, Q3_K_S is 5.7 GB, IQ3_M is 6.0 GB, Q3_K is 6.3 GB and 16 more.
What context length does Cendol Llama2 13b Merged support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 6.7 GB at 8K and 3.4 GB at 4K.
Where can I download Cendol Llama2 13b Merged GGUF?
The files are on Hugging Face in the RichardErkhov/indonlp_-_cendol-llama2-13b-merged-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 Cendol Llama2 13b Merged 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 this model on 8 GB VRAM?
Yes, using the Q4_K_M quantization which requires about 15.1 GB memory at 8k context, which fits within 8 GB VRAM when using efficient memory management.
Does it support other languages besides Indonesian?
The model is fine‑tuned for Indonesian, Sundanese, and Javanese; other languages are not supported.
Is there a vision capability?
No, the model has no vision support.