LA

latxa-70b-v1.2

LatxaGGUF by mradermacherUpdated 2024-07-03
Download on Hugging Face
Parameters69B
Context4K
Layers80
Architecturellama
Smallest quant25.5 GB
Quick answer

latxa-70b-v1.2 needs about 44.6 GB of memory at Q4_K_M (a 41.4 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 12 quants, from 25.5 GB (Q2_K) to 48.8 GB (Q5_K_M).

Latxa 70b v1.2 – a 70B‑parameter Basque language model

Latxa 70b v1.2 is a 70B‑parameter LLaMA‑based model trained 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 tasks
  • Large context handling
  • Open‑source research

Limits

  • No vision support
  • Requires 8k context for full performance
  • License allows commercial use but no fine‑tuning

Best for

  • Basque NLP research
  • Large‑scale text generation
  • Baseline comparison for low‑resource LLMs

Who it’s for. Researchers and developers working with Basque language data who need a large, open‑source LLM. The model is suitable for academic projects and commercial applications that comply with the llama2 license.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K25.5 GB 27.3 GB
Too big Get file →
IQ3_XS28.3 GB 30.2 GB
Too big Get file →
IQ3_S29.9 GB 31.8 GB
Too big Get file →
Q3_K_S29.9 GB 31.8 GB
Too big Get file →
IQ3_M30.9 GB 32.8 GB
Too big Get file →
Q3_K_M33.3 GB 35.1 GB
Too big Get file →
Q3_K_L36.1 GB 38.0 GB
Too big Get file →
IQ4_XS37.2 GB 39.0 GB
Too big Get file →
Q4_K_S39.2 GB 41.1 GB
Too big Get file →
Q4_K_M41.4 GB 43.3 GB
Too big Get file →
Q5_K_S47.5 GB 49.3 GB
Too big Get file →
Q5_K_M48.8 GB 50.6 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_S (file size 39.25 GB, estimated memory 42.4 GB at 8k context). For 16 GB VRAM, Q5_K_M (file size 48.75 GB, estimated memory 51.9 GB). For 32 GB VRAM, Q5_K_S (file size 47.46 GB, estimated memory 50.6 GB). Estimates are approximate.

What GPU do you need for latxa-70b-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: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 32 GB VRAM: the best quant that fits is IQ3_XS (28.3 GB file, about 31.5 GB in use).
  • 48 GB VRAM: the best quant that fits is Q4_K_M (41.4 GB file, about 44.6 GB in use).

Which latxa-70b-v1.2 quant should you choose?

Q4_K_M is the usual starting point for latxa-70b-v1.2: it balances file size and quality well. Here it is a 41.4 GB file.

If memory is tight, the smallest file is Q2_K at 25.5 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
Parameters69B
Layers80
Trained context4,096 tokens
KV cache (fp16)320 KB per token

Source

Quantized bymradermacher
FamilyLatxa
Licensellama2
Downloads (HF)1,004
Last updated2024-07-03

Frequently asked questions about latxa-70b-v1.2

How much VRAM does latxa-70b-v1.2 need?

About 44.6 GB at Q4_K_M with an 8K context window. That is the 41.4 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 latxa-70b-v1.2 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 28.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of latxa-70b-v1.2 GGUF?

It depends on the quant: Q2_K is 25.5 GB, IQ3_XS is 28.3 GB, IQ3_S is 29.9 GB, Q3_K_S is 29.9 GB, IQ3_M is 30.9 GB, Q3_K_M is 33.3 GB and 6 more.

What context length does latxa-70b-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 2.7 GB at 8K and 1.3 GB at 4K.

Where can I download latxa-70b-v1.2 GGUF?

The files are on Hugging Face in the mradermacher/latxa-70b-v1.2-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-70b-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 70b v1.2 on 8 GB VRAM?

No, the smallest quant requires at least 28.6 GB of VRAM at 8k context. You would need more memory or a smaller model.

Does the model support vision tasks?

No, Latxa 70b v1.2 is a language model only.

Is the model free for commercial use?

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

Other GGUFs of latxa-70b-v1.2

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Latxa models

All Latxa →

Other large models

All large models →