XT

xTower13B

XtowerGGUF by mradermacherUpdated 2024-06-27
Download on Hugging Face
Parameters13B
Context4K
Layers40
Architecturellama
Smallest quant4.9 GB
Quick answer

xTower13B 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 14 quants, from 4.9 GB (Q2_K) to 13.8 GB (Q8_0).

xTower13B – a 13B multilingual model for translation error explanation and correction

xTower13B is a 13B parameter model fine‑tuned on translation‑related tasks and conversational data. It supports English, Portuguese, Spanish, French, German, Dutch, Italian, Korean, Chinese, and Russian. The model is released under CC‑BY‑NC‑4.0.

Good at

  • Explaining translation errors
  • Correcting translation errors
  • Multilingual support

Limits

  • No vision support
  • Not aligned to human preferences
  • Limited to trained language pairs

Best for

  • Translation error analysis
  • Providing corrected translations
  • Multilingual QA on supported languages

Who it’s for. Developers and researchers needing a multilingual model for translation error explanation and correction. The model is suitable for academic and non‑commercial use under CC‑BY‑NC‑4.0.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K4.9 GB 8.7 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 10.9 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 →
Q8_013.8 GB 17.7 GB
Too big Get file →

For 8 GB VRAM, use Q2_K (4.85 GB, 12.1 GB memory at 8k context) or IQ3_XS (5.36 GB, 12.6 GB). For 12 GB VRAM, Q4_K_M (7.87 GB, 15.1 GB) or Q5_K_S (8.97 GB, 16.2 GB) are suitable. For 16 GB VRAM, Q6_K (10.68 GB, 17.9 GB) or Q8_0 (13.83 GB, 21 GB) provide higher quality.

What GPU do you need for xTower13B?

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: 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 Q8_0 (13.8 GB file, about 21.0 GB in use).

Which xTower13B quant should you choose?

Q4_K_M is the usual starting point for xTower13B: it balances file size and quality well. Here it is a 7.9 GB file.

The Q8_0 file is 13.8 GB, about 1.8 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 4.9 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
FamilyXtower
Downloads (HF)1,111
Last updated2024-06-27

Frequently asked questions about xTower13B

How much VRAM does xTower13B 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 xTower13B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 12.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of xTower13B GGUF?

It depends on the quant: Q2_K is 4.9 GB, IQ3_XS is 5.4 GB, IQ3_S is 5.7 GB, Q3_K_S is 5.7 GB, IQ3_M is 6.0 GB, Q3_K_M is 6.3 GB and 8 more.

What context length does xTower13B 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 xTower13B GGUF?

The files are on Hugging Face in the mradermacher/xTower13B-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 xTower13B use?

Hugging Face lists the license as cc-by-nc-4.0. 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 xTower13B on 8 GB VRAM?

Yes, using Q2_K or IQ3_XS quants will fit within 8 GB VRAM with approximate 12–13 GB memory usage at 8k context.

Does xTower13B support image inputs?

No, the model has no vision capability and only processes text.

Is the model aligned to user preferences?

No, xTower13B is not aligned to human preferences and may produce hallucinations or harmful content.

Other GGUFs of xTower13B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Xtower models

All Xtower →

Other medium models

All medium models →