UL

UltraLink LM

UltralinkGGUF by mradermacherUpdated 2024-11-07
Download on Hugging Face
Parameters13B
Context4K
Layers40
Architecturellama
Smallest quant2.9 GB
Quick answer

UltraLink LM 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 with instruction following and coding

UltraLink LM is a 13 billion‑parameter transformer trained on multilingual datasets. It follows instructions in English, French, Russian, Spanish, and Chinese. The model is released under a MIT license.

Good at

  • Coding
  • Multilingual instruction following
  • High‑quality text generation

Limits

  • 4096 token context
  • MIT license
  • No vision support

Best for

  • Code generation
  • Multilingual chat
  • Educational tutoring

Who it’s for. Developers and researchers who need a multilingual code‑capable LLM. Educators can use it for language‑learning and tutoring tasks.

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_07.4 GB 11.2 GB
Too big Get file →
Q4_07.4 GB 11.2 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, 10.1 GB RAM). For 12 GB VRAM, IQ3_S (5.66 GB, 12.9 GB RAM) is suitable. For 16 GB VRAM, Q5_K_M (9.23 GB, 16.4 GB RAM) offers a balance of size and performance. Estimates are approximate.

What GPU do you need for UltraLink LM?

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 UltraLink LM quant should you choose?

Q4_K_M is the usual starting point for UltraLink LM: 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
FamilyUltralink
Licensemit
Downloads (HF)1,394
Last updated2024-11-07

Frequently asked questions about UltraLink LM

How much VRAM does UltraLink LM 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 UltraLink LM 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 UltraLink LM 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 18 more.

What context length does UltraLink LM 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 UltraLink LM GGUF?

The files are on Hugging Face in the mradermacher/UltraLink-LM-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 UltraLink LM 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 UltraLink LM on 8 GB VRAM?

Yes, the IQ1_S quant is 2.9 GB and requires about 10.1 GB RAM at 8K context, fitting within 8 GB VRAM with some swap.

Does UltraLink LM support image inputs?

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

Other GGUFs of UltraLink-LM

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Ultralink models

All Ultralink →

Other medium models

All medium models →