BA

Bakpia-V1-0.5B-Javanese

BakpiaGGUF by mradermacherUpdated 2024-07-08
Download on Hugging Face
Parameters494M
Context32K
Layers24
Architectureqwen2
Smallest quant0.3 GB
Quick answer

Bakpia-V1-0.5B-Javanese needs about 1.0 GB of memory at Q4_K_M (a 0.4 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 15 quants, from 0.3 GB (Q3_K_S) to 1.0 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 0.4 GB.

Bakpia‑V1‑0.5B‑Javanese – a 0.5B parameter Javanese LLM

Bakpia‑V1‑0.5B‑Javanese is a 0.494 billion‑parameter model fine‑tuned for Javanese. It supports single‑turn QA across various domains and is available in multiple GGUF quantizations. The model is released under Apache‑2.0.

Good at

  • Javanese single‑turn QA
  • Synthetic data‑trained instruction following
  • Low‑parameter Javanese generation

Limits

  • No Ngoko Javanese support
  • Context limited to 32768 tokens
  • No vision capabilities

Best for

  • Javanese chatbot prototypes
  • Local Javanese text generation
  • Educational tools for Javanese language

Who it’s for. Developers and researchers needing a lightweight Javanese LLM for local deployment. The model is open source and can be run with llama.cpp on modest hardware.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_S0.3 GB 0.9 GB
Fits Get file →
IQ3_S0.3 GB 0.9 GB
Fits Get file →
IQ3_XS0.3 GB 0.9 GB
Fits Get file →
Q2_K0.3 GB 0.9 GB
Fits Get file →
IQ3_M0.3 GB 0.9 GB
Fits Get file →
IQ4_XS0.4 GB 1.0 GB
Fits Get file →
Q3_K_M0.4 GB 1.0 GB
Fits Get file →
Q3_K_L0.4 GB 1.0 GB
Fits Get file →
Q4_K_S0.4 GB 1.0 GB
Fits Get file →
Q4_K_M0.4 GB 1.0 GB
Fits Get file →
Q5_K_S0.4 GB 1.0 GB
Fits Get file →
Q5_K_M0.4 GB 1.0 GB
Fits Get file →
Q6_K0.5 GB 1.1 GB
Fits Get file →
Q8_00.5 GB 1.1 GB
Fits Get file →
F161.0 GB 1.6 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_S (0.39 GB file, ~1 GB memory). For 4 GB VRAM, use Q3_K_S or IQ3_S (0.34 GB file, ~0.9 GB memory). For higher precision, use F16 (0.99 GB file, ~1.6 GB memory).

What GPU do you need for Bakpia-V1-0.5B-Javanese?

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: the best quant that fits is F16 (1.0 GB file, about 1.6 GB in use).

Which Bakpia-V1-0.5B-Javanese quant should you choose?

Q4_K_M is the usual starting point for Bakpia-V1-0.5B-Javanese: it balances file size and quality well. Here it is a 0.4 GB file.

The Q8_0 file is 0.5 GB, about 1.3 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 Q3_K_S at 0.3 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen2
Parameters494M
Layers24
Trained context32,768 tokens
KV cache (fp16)12 KB per token

Source

Quantized bymradermacher
FamilyBakpia
Licenseapache-2.0
Downloads (HF)786
Last updated2024-07-08

Frequently asked questions about Bakpia-V1-0.5B-Javanese

How much VRAM does Bakpia-V1-0.5B-Javanese need?

About 1.0 GB at Q4_K_M with an 8K context window. That is the 0.4 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 Bakpia-V1-0.5B-Javanese on an 8 GB GPU?

Yes, with F16: the 1.0 GB file needs about 1.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Bakpia-V1-0.5B-Javanese GGUF?

It depends on the quant: Q3_K_S is 0.3 GB, IQ3_S is 0.3 GB, IQ3_XS is 0.3 GB, Q2_K is 0.3 GB, IQ3_M is 0.3 GB, IQ4_XS is 0.4 GB and 9 more.

What context length does Bakpia-V1-0.5B-Javanese support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.4 GB at 32K.

Where can I download Bakpia-V1-0.5B-Javanese GGUF?

The files are on Hugging Face in the mradermacher/Bakpia-V1-0.5B-Javanese-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 Bakpia-V1-0.5B-Javanese 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 Bakpia‑V1‑0.5B‑Javanese on 8 GB VRAM?

Yes, the Q4_K_S quant uses about 1 GB memory at 8 k context, fitting within 8 GB VRAM.

Does the model support Ngoko Javanese?

No, Ngoko Javanese is not currently supported; only Krama Javanese is available.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Bakpia models

All Bakpia →

Other tiny models

All tiny models →