KO

Koala 13B HF

KoalaGGUF by mradermacherUpdated 2025-03-04
Download on Hugging Face
Parameters13B
Context2K
Layers40
Architecturellama
Smallest quant2.9 GB
Quick answer

Koala 13B HF 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 24 quants, from 2.9 GB (IQ1_S) to 10.7 GB (Q6_K).

Koala 13B HF – a 13‑billion‑parameter dialogue model

Koala 13B HF is a 13‑billion‑parameter llama architecture model trained on 2048 context tokens. It is available in multiple GGUF quantizations for llama.cpp. The model is intended for academic research.

Good at

  • Academic dialogue tasks
  • Research prototyping
  • LLM experimentation

Limits

  • No vision support
  • License is other – academic use only
  • Requires 8‑k context for estimates

Best for

  • Academic research projects
  • LLM fine‑tuning experiments
  • Prototype chat applications

Who it’s for. Researchers and developers who need a 13B llama‑style model for dialogue tasks and want to experiment with different quantizations. The model is suitable for academic projects and prototyping.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S2.9 GB 5.1 GB
Fits Get file →
IQ1_M3.1 GB 5.3 GB
Fits Get file →
IQ2_XXS3.5 GB 5.7 GB
Fits Get file →
IQ2_XS3.9 GB 6.1 GB
Fits Get file →
IQ2_S4.2 GB 6.4 GB
Fits Get file →
Q2_K_S4.4 GB 6.6 GB
Fits Get file →
IQ2_M4.5 GB 6.7 GB
Fits Get file →
Q2_K4.9 GB 7.0 GB
Fits Get file →
IQ3_XXS5.0 GB 7.1 GB
Fits Get file →
IQ3_XS5.4 GB 7.5 GB
Tight Get file →
IQ3_S5.7 GB 7.8 GB
Tight Get file →
Q3_K_S5.7 GB 7.8 GB
Tight Get file →
IQ3_M6.0 GB 8.2 GB
Too big Get file →
Q3_K_M6.3 GB 8.5 GB
Too big Get file →
Q3_K_L6.9 GB 9.1 GB
Too big Get file →
IQ4_XS7.0 GB 9.1 GB
Too big Get file →
IQ4_NL7.4 GB 9.5 GB
Too big Get file →
Q4_07.4 GB 9.6 GB
Too big Get file →
Q4_K_S7.4 GB 9.6 GB
Too big Get file →
Q4_K_M7.9 GB 10.0 GB
Too big Get file →
Q4_18.2 GB 10.3 GB
Too big Get file →
Q5_K_S9.0 GB 11.2 GB
Too big Get file →
Q5_K_M9.2 GB 11.4 GB
Too big Get file →
Q6_K10.7 GB 12.9 GB
Too big Get file →

For 8‑GB VRAM, use IQ1_S (2.9 GB) or IQ1_M (3.14 GB). With 16‑GB VRAM, Q4_0 (7.39 GB) or Q4_K_M (7.87 GB) are good choices. For 24‑GB VRAM, Q5_K_S (8.97 GB) or Q6_K (10.68 GB) provide higher quality. Memory estimates are approximate.

What GPU do you need for Koala 13B HF?

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: the best quant that fits is IQ2_M (4.5 GB file, about 11.7 GB in use).
  • 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 Q6_K (10.7 GB file, about 17.9 GB in use).

Which Koala 13B HF quant should you choose?

Q4_K_M is the usual starting point for Koala 13B HF: it balances file size and quality well. Here it is a 7.9 GB file.

If memory is tight, the smallest file is IQ1_S at 2.9 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

Architecturellama
Parameters13B
Layers40
Trained context2,048 tokens
KV cache (fp16)800 KB per token

Source

Quantized bymradermacher
FamilyKoala
Licenseother
Downloads (HF)1,142
Last updated2025-03-04

Frequently asked questions about Koala 13B HF

How much VRAM does Koala 13B HF 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 Koala 13B HF on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 10.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Koala 13B HF GGUF?

It depends on the quant: IQ1_S is 2.9 GB, IQ1_M is 3.1 GB, IQ2_XXS is 3.5 GB, IQ2_XS is 3.9 GB, IQ2_S is 4.2 GB, Q2_K_S is 4.4 GB and 18 more.

What context length does Koala 13B HF support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 6.7 GB at 8K and 1.7 GB at 2K.

Where can I download Koala 13B HF GGUF?

The files are on Hugging Face in the mradermacher/koala-13B-HF-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 Koala 13B HF use?

Hugging Face lists the license as other. 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 Koala 13B HF on 8 GB VRAM?

Yes, use the IQ1_S or IQ1_M GGUF files; they require about 10.1–10.3 GB of VRAM at 8‑k context.

Does Koala 13B HF support vision?

No, the model has no vision capabilities.

What is the context length of Koala 13B HF?

The model was trained with 2048 context tokens.

Other GGUFs of koala-13B-HF

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Koala models

All Koala →

Other medium models

All medium models →