LA

latxa-13b-v1.2

LatxaGGUF by mradermacherUpdated 2024-08-02
Download on Hugging Face
Parameters13B
Context4K
Layers40
Architecturellama
Smallest quant2.9 GB
Quick answer

latxa-13b-v1.2 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 21 quants, from 2.9 GB (IQ1_S) to 10.7 GB (Q6_K).

Latxa 13B LLaMA‑2 based Basque language model

Latxa 13B is a 13‑billion‑parameter LLaMA‑2 model fine‑tuned on a Basque corpus. It supports English and Basque and is released under the llama2 license. The model is available in multiple GGUF quantizations.

Good at

  • Basque language generation
  • English‑Basque bilingual tasks
  • Large‑context reasoning up to 4096 tokens

Limits

  • No vision support
  • Requires 8‑k context for memory estimates
  • License allows commercial use but no pre‑training data redistribution

Best for

  • Basque content creation
  • Bilingual translation assistance
  • Research on low‑resource language models

Who it’s for. Researchers and developers working with Basque language data. The model is suitable for academic projects and commercial applications that require Basque language understanding.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S2.9 GB 6.8 GB
Fits Get file →
IQ1_M3.1 GB 7.0 GB
Fits Get file →
IQ2_XXS3.5 GB 7.4 GB
Tight Get file →
IQ2_XS3.9 GB 7.7 GB
Tight Get file →
IQ2_S4.2 GB 8.1 GB
Too big Get file →
IQ2_M4.5 GB 8.4 GB
Too big Get file →
Q2_K4.9 GB 8.7 GB
Too big Get file →
IQ3_XXS5.0 GB 8.8 GB
Too big Get file →
IQ3_XS5.4 GB 9.2 GB
Too big Get file →
IQ3_S5.7 GB 9.5 GB
Too big Get file →
Q3_K_S5.7 GB 9.5 GB
Too big Get file →
IQ3_M6.0 GB 9.8 GB
Too big Get file →
Q3_K_M6.3 GB 10.2 GB
Too big Get file →
Q3_K_L6.9 GB 10.8 GB
Too big Get file →
IQ4_XS7.0 GB 10.8 GB
Too big Get file →
Q4_07.4 GB 11.2 GB
Too big Get file →
Q4_K_S7.4 GB 11.3 GB
Too big Get file →
Q4_K_M7.9 GB 11.7 GB
Too big Get file →
Q5_K_S9.0 GB 12.8 GB
Too big Get file →
Q5_K_M9.2 GB 13.1 GB
Too big Get file →
Q6_K10.7 GB 14.5 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (2.9 GB) or IQ1_M (3.14 GB). For 12 GB VRAM, IQ2_S (4.2 GB) or Q2_K (4.85 GB) are good choices. Larger VRAM allows higher‑quality quants such as Q4_K_M (7.87 GB). Memory estimates are approximate.

What GPU do you need for latxa-13b-v1.2?

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_K_M (7.9 GB file, about 15.1 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 latxa-13b-v1.2 quant should you choose?

Q4_K_M is the usual starting point for latxa-13b-v1.2: 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 context4,096 tokens
KV cache (fp16)800 KB per token

Source

Quantized bymradermacher
FamilyLatxa
Licensellama2
Downloads (HF)10,276
Last updated2024-08-02

Frequently asked questions about latxa-13b-v1.2

How much VRAM does latxa-13b-v1.2 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 latxa-13b-v1.2 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 latxa-13b-v1.2 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, IQ2_M is 4.5 GB and 15 more.

What context length does latxa-13b-v1.2 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 latxa-13b-v1.2 GGUF?

The files are on Hugging Face in the mradermacher/latxa-13b-v1.2-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 latxa-13b-v1.2 use?

Hugging Face lists the license as llama2. 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 Latxa 13B on 8 GB VRAM?

Yes, with the IQ1_S or IQ1_M quant, which use about 10 GB of VRAM at 8‑k context.

Does Latxa support image input?

No, the model is a text‑only language model.

Is the model licensed for commercial use?

Yes, it is released under the llama2 license, which permits commercial use.

Other GGUFs of latxa-13b-v1.2

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Latxa models

All Latxa →

Other medium models

All medium models →