SA

SambaLingo Serbian Base

SambalingoGGUF by mradermacherUpdated 2024-12-12
Download on Hugging Face
Parameters6.95B
Context4K
Layers32
Architecturellama
Smallest quant1.6 GB
Quick answer

SambaLingo Serbian Base needs about 9.0 GB of memory at Q4_K_M (a 4.2 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 25 quants, from 1.6 GB (IQ1_S) to 5.7 GB (Q6_K).

SambaLingo Serbian Base – a 6.95B Llama‑2 model fine‑tuned for Serbian and English

SambaLingo Serbian Base is a 6.95B parameter Llama‑2 model adapted to Serbian and English. It was trained on 17 billion tokens from the Cultura‑X Serbian split. The model supports a 4096 token context window.

Good at

  • Serbian language generation
  • English‑Serbian translation
  • Few‑shot prompting

Limits

  • No vision support
  • Requires 4096 token context
  • License is llama2

Best for

  • Chatbot prototypes
  • Translation tasks
  • Language learning tools

Who it’s for. Developers building Serbian‑English applications who need a pretrained Llama‑2 base. The model is suitable for research and production use where a bilingual LLM is required.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S1.6 GB 4.3 GB
Fits Get file →
IQ1_M1.8 GB 4.4 GB
Fits Get file →
IQ2_XXS2.0 GB 4.6 GB
Fits Get file →
IQ2_XS2.1 GB 4.8 GB
Fits Get file →
IQ2_S2.3 GB 5.0 GB
Fits Get file →
Q2_K_S2.4 GB 5.1 GB
Fits Get file →
IQ2_M2.5 GB 5.1 GB
Fits Get file →
Q2_K2.7 GB 5.3 GB
Fits Get file →
IQ3_XXS2.7 GB 5.3 GB
Fits Get file →
IQ3_XS2.9 GB 5.6 GB
Fits Get file →
IQ3_S3.1 GB 5.7 GB
Fits Get file →
Q3_K_S3.1 GB 5.7 GB
Fits Get file →
IQ3_M3.2 GB 5.9 GB
Fits Get file →
Q3_K_M3.4 GB 6.1 GB
Fits Get file →
Q3_K_L3.7 GB 6.4 GB
Fits Get file →
IQ4_XS3.8 GB 6.4 GB
Fits Get file →
Q4_04.0 GB 6.6 GB
Fits Get file →
Q4_04.0 GB 6.6 GB
Fits Get file →
Q4_04.0 GB 6.6 GB
Fits Get file →
Q4_04.0 GB 6.6 GB
Fits Get file →
Q4_K_S4.0 GB 6.6 GB
Fits Get file →
Q4_K_M4.2 GB 6.9 GB
Fits Get file →
Q5_K_S4.8 GB 7.5 GB
Tight Get file →
Q5_K_M4.9 GB 7.6 GB
Tight Get file →
Q6_K5.7 GB 8.3 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (1.63 GB, 6.4 GB memory at 8k context) or IQ1_M (1.76 GB, 6.6 GB). For 12 GB VRAM, Q4_K_M (4.23 GB, 9 GB) or Q5_K_M (4.94 GB, 9.7 GB) are good choices. Larger VRAM allows higher‑quality quants like Q6_K (5.7 GB, 10.5 GB).

What GPU do you need for SambaLingo Serbian Base?

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: the best quant that fits is IQ3_M (3.2 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (5.7 GB file, about 10.5 GB in use).

Which SambaLingo Serbian Base quant should you choose?

Q4_K_M is the usual starting point for SambaLingo Serbian Base: it balances file size and quality well. Here it is a 4.2 GB file.

If memory is tight, the smallest file is IQ1_S at 1.6 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
Parameters6.95B
Layers32
Trained context4,096 tokens
KV cache (fp16)512 KB per token

Source

Quantized bymradermacher
Licensellama2
Downloads (HF)483
Last updated2024-12-12

Frequently asked questions about SambaLingo Serbian Base

How much VRAM does SambaLingo Serbian Base need?

About 9.0 GB at Q4_K_M with an 8K context window. That is the 4.2 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 SambaLingo Serbian Base on an 8 GB GPU?

Yes, with IQ3_M: the 3.2 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of SambaLingo Serbian Base GGUF?

It depends on the quant: IQ1_S is 1.6 GB, IQ1_M is 1.8 GB, IQ2_XXS is 2.0 GB, IQ2_XS is 2.1 GB, IQ2_S is 2.3 GB, Q2_K_S is 2.4 GB and 19 more.

What context length does SambaLingo Serbian Base support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 4.3 GB at 8K and 2.1 GB at 4K.

Where can I download SambaLingo Serbian Base GGUF?

The files are on Hugging Face in the mradermacher/SambaLingo-Serbian-Base-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 SambaLingo Serbian Base 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 this model on 8 GB VRAM?

Yes, use IQ1_S or IQ1_M quants; they require about 6.4–6.6 GB memory at 8k context.

Does the model support vision inputs?

No, the model only handles text.

What is the context length?

The model supports a 4096 token context window.

Other GGUFs of SambaLingo-Serbian-Base

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Sambalingo models

All Sambalingo →

Other small models

All small models →