KA

kalisai Nusantara 2.7b Indo Chat

KalisaiGGUF by RichardErkhovUpdated 2024-09-21
Download on Hugging Face
Parameters2.65B
Context8K
Layers40
Architectureqwen2
Smallest quant1.2 GB
Quick answer

kalisai Nusantara 2.7b Indo Chat needs about 4.9 GB of memory at Q4_K_M (a 1.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 22 quants, from 1.2 GB (Q2_K) to 2.8 GB (Q8_0).

kalisai Nusantara 2.7b Indo Chat – 2.65B parameter Qwen2 model

kalisai Nusantara 2.7b Indo Chat is a 2.65B parameter Qwen2 language model fine‑tuned for Indonesian and English conversational tasks. It supports 8192 token context and is released under the Apache‑2.0 license.

Good at

  • Conversational Indonesian language
  • English‑Indonesian bilingual dialogue
  • Domain‑specific Indonesian content

Limits

  • No vision support
  • Requires 8k context for full performance
  • License is Apache‑2.0

Best for

  • Chatbots in Indonesian
  • Local language content generation
  • Bilingual support for Indonesian and English

Who it’s for. Developers building Indonesian language chat applications or content generators. Researchers needing a lightweight Indonesian‑focused model for experimentation.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1.2 GB 4.4 GB
Fits Get file →
IQ3_XS1.3 GB 4.5 GB
Fits Get file →
IQ3_S1.3 GB 4.5 GB
Fits Get file →
Q3_K_S1.3 GB 4.5 GB
Fits Get file →
IQ3_M1.4 GB 4.6 GB
Fits Get file →
Q3_K1.4 GB 4.6 GB
Fits Get file →
Q3_K_M1.4 GB 4.6 GB
Fits Get file →
Q3_K_L1.5 GB 4.7 GB
Fits Get file →
IQ4_XS1.5 GB 4.7 GB
Fits Get file →
Q4_01.6 GB 4.8 GB
Fits Get file →
IQ4_NL1.6 GB 4.8 GB
Fits Get file →
Q4_K_S1.6 GB 4.8 GB
Fits Get file →
Q4_11.7 GB 4.9 GB
Fits Get file →
Q4_K1.7 GB 4.9 GB
Fits Get file →
Q4_K_M1.7 GB 4.9 GB
Fits Get file →
Q5_01.9 GB 5.1 GB
Fits Get file →
Q5_K_S1.9 GB 5.1 GB
Fits Get file →
Q5_K2.0 GB 5.2 GB
Fits Get file →
Q5_K_M2.0 GB 5.2 GB
Fits Get file →
Q5_12.0 GB 5.2 GB
Fits Get file →
Q6_K2.3 GB 5.5 GB
Fits Get file →
Q8_02.8 GB 6.0 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (1.74 GB file, ~4.9 GB memory). For 12 GB VRAM, Q5_K_M (1.98 GB file, ~5.2 GB memory) offers higher precision. For 16 GB VRAM, Q6_K (2.29 GB file, ~5.5 GB memory) provides the best trade‑off.

What GPU do you need for kalisai Nusantara 2.7b 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 Q8_0 (2.8 GB file, about 6.0 GB in use).

Which kalisai Nusantara 2.7b Indo Chat quant should you choose?

Q4_K_M is the usual starting point for kalisai Nusantara 2.7b Indo Chat: it balances file size and quality well. Here it is a 1.7 GB file.

The Q8_0 file is 2.8 GB, about 1.6 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 1.2 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
Parameters2.65B
Layers40
Trained context8,192 tokens
KV cache (fp16)320 KB per token

Source

Quantized byRichardErkhov
FamilyKalisai
Licenseapache-2.0
Downloads (HF)647
Last updated2024-09-21

Frequently asked questions about kalisai Nusantara 2.7b Indo Chat

How much VRAM does kalisai Nusantara 2.7b Indo Chat need?

About 4.9 GB at Q4_K_M with an 8K context window. That is the 1.7 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 kalisai Nusantara 2.7b Indo Chat on an 8 GB GPU?

Yes, with Q8_0: the 2.8 GB file needs about 6.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of kalisai Nusantara 2.7b Indo Chat GGUF?

It depends on the quant: Q2_K is 1.2 GB, IQ3_XS is 1.3 GB, IQ3_S is 1.3 GB, Q3_K_S is 1.3 GB, IQ3_M is 1.4 GB, Q3_K is 1.4 GB and 16 more.

What context length does kalisai Nusantara 2.7b Indo Chat support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 2.7 GB at 8K and 2.7 GB at 8K.

Where can I download kalisai Nusantara 2.7b Indo Chat GGUF?

The files are on Hugging Face in the RichardErkhov/kalisai_-_Nusantara-2.7b-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 kalisai Nusantara 2.7b 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 this model on 8 GB VRAM?

Yes, the Q4_K_M quantization requires about 4.9 GB of VRAM at 8k context, which fits within an 8 GB GPU.

Does the model support vision tasks?

No, the model is text‑only and does not include vision capabilities.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Similar models

Browse all →

More from RichardErkhov

All by RichardErkhov →

More Kalisai models

All Kalisai →

Other tiny models

All tiny models →