SambaLingo Bulgarian 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 Bulgarian Base – a 6.95B Llama‑2 model fine‑tuned for Bulgarian and English
SambaLingo Bulgarian Base is a 6.95B parameter Llama‑2 model adapted to Bulgarian by training on 38 billion tokens from the Cultura‑X dataset. It supports 4096‑token context and is released under the llama2 license.
Good at
- Bulgarian language tasks
- English‑Bulgarian translation
- Few‑shot prompting
Limits
- No vision support
- Requires 8 k context for memory estimates
- License is llama2
Best for
- Chatbot prototypes in Bulgarian
- Translation pipelines
- Language model research
Who it’s for. Developers and researchers who need a Bulgarian‑English language model with a moderate parameter count. The model is suitable for applications that can run on a GPU with at least 8 GB VRAM and support 8 k context length.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 1.6 GB | 4.3 GB | Fits | Get file → | |
| IQ1_M | 1.8 GB | 4.4 GB | Fits | Get file → | |
| IQ2_XXS | 2.0 GB | 4.6 GB | Fits | Get file → | |
| IQ2_XS | 2.1 GB | 4.8 GB | Fits | Get file → | |
| IQ2_S | 2.3 GB | 5.0 GB | Fits | Get file → | |
| Q2_K_S | 2.4 GB | 5.1 GB | Fits | Get file → | |
| IQ2_M | 2.5 GB | 5.1 GB | Fits | Get file → | |
| Q2_K | 2.7 GB | 5.3 GB | Fits | Get file → | |
| IQ3_XXS | 2.7 GB | 5.3 GB | Fits | Get file → | |
| IQ3_XS | 2.9 GB | 5.6 GB | Fits | Get file → | |
| IQ3_S | 3.1 GB | 5.7 GB | Fits | Get file → | |
| Q3_K_S | 3.1 GB | 5.7 GB | Fits | Get file → | |
| IQ3_M | 3.2 GB | 5.9 GB | Fits | Get file → | |
| Q3_K_M | 3.4 GB | 6.1 GB | Fits | Get file → | |
| Q3_K_L | 3.7 GB | 6.4 GB | Fits | Get file → | |
| IQ4_XS | 3.8 GB | 6.4 GB | Fits | Get file → | |
| Q4_0 | 4.0 GB | 6.6 GB | Fits | Get file → | |
| Q4_0 | 4.0 GB | 6.6 GB | Fits | Get file → | |
| Q4_0 | 4.0 GB | 6.6 GB | Fits | Get file → | |
| Q4_0 | 4.0 GB | 6.6 GB | Fits | Get file → | |
| Q4_K_S | 4.0 GB | 6.6 GB | Fits | Get file → | |
| Q4_K_M | 4.2 GB | 6.9 GB | Fits | Get file → | |
| Q5_K_S | 4.8 GB | 7.5 GB | Tight | Get file → | |
| Q5_K_M | 4.9 GB | 7.6 GB | Tight | Get file → | |
| Q6_K | 5.7 GB | 8.3 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (1.63 GB file, 6.4 GB memory) or IQ1_M (1.76 GB file, 6.6 GB memory). If more VRAM is available, IQ2_S (2.31 GB file, 7.1 GB memory) or Q4_K_M (4.23 GB file, 9 GB memory) provide better quality. Memory estimates are approximate.
What GPU do you need for SambaLingo Bulgarian 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 Bulgarian Base quant should you choose?
Q4_K_M is the usual starting point for SambaLingo Bulgarian 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
Frequently asked questions about SambaLingo Bulgarian Base
How much VRAM does SambaLingo Bulgarian 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 Bulgarian 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 Bulgarian 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 Bulgarian 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 Bulgarian Base GGUF?
The files are on Hugging Face in the mradermacher/SambaLingo-Bulgarian-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 Bulgarian 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, the IQ1_S and IQ1_M quantizations fit within 8 GB VRAM with an estimated memory usage of 6.4–6.6 GB at 8 k context.
Does this model support vision tasks?
No, the model is a language model only and does not include vision capabilities.
What context length does it support?
It supports a context length of 4096 tokens, which is the trained context size.