XALMA 13B Pretrain 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).
13B multilingual LLM supporting 50 languages
XALMA 13B Pretrain is a 13B‑parameter LLM trained on 50 languages. It uses a plug‑and‑play architecture with language‑specific modules and a 4096‑token context window. The model is released under the MIT license.
Good at
- Multilingual translation
- Open‑ended QA across 50 languages
- Plug‑and‑play language modules
Limits
- Trained with 4096‑token context
- MoE requires large GPU memory
- No vision capabilities
Best for
- Translation tasks
- Multilingual QA
- Research on language‑specific modules
Who it’s for. Developers and researchers who need a multilingual LLM with a modular architecture. The model is suitable for applications requiring translation or open‑ended QA across many languages.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 2.9 GB | 6.8 GB | Fits | Get file → | |
| IQ1_M | 3.1 GB | 7.0 GB | Fits | Get file → | |
| IQ2_XXS | 3.5 GB | 7.4 GB | Tight | Get file → | |
| IQ2_XS | 3.9 GB | 7.7 GB | Tight | Get file → | |
| IQ2_S | 4.2 GB | 8.1 GB | Too big | Get file → | |
| Q2_K_S | 4.4 GB | 8.3 GB | Too big | Get file → | |
| IQ2_M | 4.5 GB | 8.4 GB | Too big | Get file → | |
| Q2_K | 4.9 GB | 8.7 GB | Too big | Get file → | |
| IQ3_XXS | 5.0 GB | 8.8 GB | Too big | Get file → | |
| IQ3_XS | 5.4 GB | 9.2 GB | Too big | Get file → | |
| IQ3_S | 5.7 GB | 9.5 GB | Too big | Get file → | |
| Q3_K_S | 5.7 GB | 9.5 GB | Too big | Get file → | |
| IQ3_M | 6.0 GB | 9.8 GB | Too big | Get file → | |
| Q3_K_M | 6.3 GB | 10.2 GB | Too big | Get file → | |
| Q3_K_L | 6.9 GB | 10.8 GB | Too big | Get file → | |
| IQ4_XS | 7.0 GB | 10.8 GB | Too big | Get file → | |
| IQ4_NL | 7.4 GB | 11.2 GB | Too big | Get file → | |
| Q4_0 | 7.4 GB | 11.2 GB | Too big | Get file → | |
| Q4_K_S | 7.4 GB | 11.3 GB | Too big | Get file → | |
| Q4_K_M | 7.9 GB | 11.7 GB | Too big | Get file → | |
| Q4_1 | 8.2 GB | 12.0 GB | Too big | Get file → | |
| Q5_K_S | 9.0 GB | 12.8 GB | Too big | Get file → | |
| Q5_K_M | 9.2 GB | 13.1 GB | Too big | Get file → | |
| Q6_K | 10.7 GB | 14.5 GB | Too big | Get file → |
For a 16‑GB VRAM setup, the Q4_K_M quant (file size 7.87 GB, estimated 15.1 GB memory at 8k context) is a good balance. If you have 32 GB VRAM, the Q6_K quant (10.68 GB, 17.9 GB memory) offers higher quality. Smaller quants such as IQ1_S (2.9 GB, 10.1 GB memory) are suitable for limited memory but still exceed 8‑GB VRAM limits.
What GPU do you need for XALMA 13B Pretrain?
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 XALMA 13B Pretrain quant should you choose?
Q4_K_M is the usual starting point for XALMA 13B Pretrain: 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
Source
Frequently asked questions about XALMA 13B Pretrain
How much VRAM does XALMA 13B Pretrain 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 XALMA 13B Pretrain 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 XALMA 13B Pretrain 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 XALMA 13B Pretrain 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 XALMA 13B Pretrain GGUF?
The files are on Hugging Face in the mradermacher/X-ALMA-13B-Pretrain-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 XALMA 13B Pretrain use?
Hugging Face lists the license as mit. 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 XALMA 13B on 8 GB VRAM?
No, the smallest quant requires at least 10.1 GB memory at 8k context, exceeding 8 GB VRAM.
Does XALMA 13B support vision tasks?
No, the model has no vision capabilities.
What license is XALMA 13B released under?
The model is released under the MIT license.