Llama Leonida needs about 6.6 GB of memory at Q4_K_M (a 5.0 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 25 quants, from 0.0 GB to 6.7 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
8‑billion‑parameter Llama 3.1 model for Greek↔Tsakonian translation
Llama Leonida is an 8.2‑billion‑parameter Llama 3.1 model trained to translate between Modern Greek and Tsakonian. It uses the Kostakis orthography and is fine‑tuned on 17,960 sentence pairs followed by reinforcement learning on 2,819 pairs. The model runs locally with a Q4_K_M quantization.
Good at
- Greek↔Tsakonian translation
- Kostakis orthography support
- LLama 3.1 chat template
Limits
- No vision support
- Requires 8‑k context for estimates
- License: llama3.1
Best for
- Local translation of Greek and Tsakonian
- Educational language tools
- Research on endangered languages
Who it’s for. Developers and researchers needing a lightweight, open‑source Greek‑Tsakonian translation model. It is suitable for laptops and small servers that can handle the 8‑billion‑parameter size with a Q4_K_M quantization.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.6 GB | Fits | Get file → | |
| IQ1_S | 2.1 GB | 3.7 GB | Fits | Get file → | |
| IQ1_M | 2.3 GB | 3.8 GB | Fits | Get file → | |
| IQ2_XXS | 2.5 GB | 4.1 GB | Fits | Get file → | |
| IQ2_XS | 2.7 GB | 4.3 GB | Fits | Get file → | |
| IQ2_S | 2.9 GB | 4.4 GB | Fits | Get file → | |
| IQ2_M | 3.0 GB | 4.6 GB | Fits | Get file → | |
| Q2_K_S | 3.1 GB | 4.7 GB | Fits | Get file → | |
| Q2_K | 3.3 GB | 4.9 GB | Fits | Get file → | |
| IQ3_XXS | 3.4 GB | 4.9 GB | Fits | Get file → | |
| IQ3_XS | 3.6 GB | 5.2 GB | Fits | Get file → | |
| Q3_K_S | 3.8 GB | 5.3 GB | Fits | Get file → | |
| IQ3_S | 3.8 GB | 5.4 GB | Fits | Get file → | |
| IQ3_M | 3.9 GB | 5.5 GB | Fits | Get file → | |
| Q3_K_M | 4.1 GB | 5.7 GB | Fits | Get file → | |
| Q3_K_L | 4.4 GB | 6.0 GB | Fits | Get file → | |
| IQ4_XS | 4.6 GB | 6.1 GB | Fits | Get file → | |
| Q4_0 | 4.8 GB | 6.4 GB | Fits | Get file → | |
| IQ4_NL | 4.8 GB | 6.4 GB | Fits | Get file → | |
| Q4_K_S | 4.8 GB | 6.4 GB | Fits | Get file → | |
| Q4_K_M | 5.0 GB | 6.6 GB | Fits | Get file → | |
| Q4_1 | 5.3 GB | 6.8 GB | Fits | Get file → | |
| Q5_K_S | 5.7 GB | 7.3 GB | Tight | Get file → | |
| Q5_K_M | 5.9 GB | 7.4 GB | Tight | Get file → | |
| Q6_K | 6.7 GB | 8.3 GB | Too big | Get file → |
For 8‑GB VRAM, use the Q4_K_M file (4.13 GB, 5.7 GB memory at 8k context). For 12‑GB VRAM, Q4_K_L (4.43 GB, 6 GB memory) is a good balance. If more VRAM is available, Q5_K_M (5.86 GB, 7.4 GB memory) offers higher quality.
What GPU do you need for Llama Leonida?
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: the best quant that fits is IQ1_M (2.3 GB file, about 3.8 GB in use).
- 6 GB VRAM: the best quant that fits is Q3_K_L (4.4 GB file, about 6.0 GB in use).
- 8 GB VRAM: the best quant that fits is Q5_K_M (5.9 GB file, about 7.4 GB in use).
- 12 GB VRAM: the best quant that fits is Q6_K (6.7 GB file, about 8.3 GB in use).
Which Llama Leonida quant should you choose?
Q4_K_M is the usual starting point for Llama Leonida: it balances file size and quality well. Here it is a 5.0 GB file.
If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Llama Leonida
How much VRAM does Llama Leonida need?
About 6.6 GB at Q4_K_M with an 8K context window. That is the 5.0 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 Llama Leonida on an 8 GB GPU?
Yes, with Q5_K_M: the 5.9 GB file needs about 7.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Llama Leonida GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 2.1 GB, IQ1_M is 2.3 GB, IQ2_XXS is 2.5 GB, IQ2_XS is 2.7 GB, IQ2_S is 2.9 GB and 19 more.
What context length does Llama Leonida support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.
Where can I download Llama Leonida GGUF?
The files are on Hugging Face in the mradermacher/Llama-Leonida-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 Llama Leonida use?
Hugging Face lists the license as llama3.1. 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 Llama Leonida on 8 GB VRAM?
Yes, the Q4_K_M quantization (4.13 GB file, 5.7 GB memory at 8k context) fits within 8 GB VRAM.
Does the model support image input?
No, Llama Leonida does not have vision capabilities.
What context length does it support?
It was trained on 131072 tokens and can run with an 8k context length.