tabis sakha slm needs about 1.4 GB of memory at its main file (a 0.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 0.5 GB to 2.7 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.
Tabis Sakha SLM – a small bilingual model for Yakut and Russian
Tabis Sakha SLM is a 0.752‑billion‑parameter Qwen 3.5‑based model fine‑tuned for the Yakut language and Russian‑Yakut translation. It was trained on a parallel corpus and quantized with QLoRA 4‑bit for efficient local deployment.
Good at
- Yakut language tasks
- Russian‑Yakut translation
- Reasoning and tool use
Limits
- No vision support beyond text
- Large context requires 262144 tokens
- License is Apache‑2.0
Best for
- Local translation tools
- Educational language apps
- Research prototyping
Who it’s for. Developers and researchers needing a lightweight, bilingual model for Yakut and Russian. The model runs on consumer GPUs and does not require internet access.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.5 GB | 1.4 GB | Fits | Get file → | |
| — | 2.7 GB | 3.6 GB | Fits | Get file → |
For 4–8 GB VRAM, use the 0.53 GB GGUF file (≈1.4 GB RAM at 8 k context). For 8–12 GB VRAM, use the 2.71 GB GGUF file (≈3.6 GB RAM at 8 k context).
What GPU do you need for tabis sakha slm?
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 the main file (2.7 GB file, about 3.6 GB in use).
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about tabis sakha slm
How much VRAM does tabis sakha slm need?
About 1.4 GB at its main file with an 8K context window. That is the 0.5 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 tabis sakha slm on an 8 GB GPU?
Yes, with the smaller files: the 2.7 GB file needs about 3.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of tabis sakha slm GGUF?
It depends on the quant: file is 0.5 GB, file is 2.7 GB.
What context length does tabis sakha slm support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.6 GB at 32K.
Where can I download tabis sakha slm GGUF?
The files are on Hugging Face in the chairus/tabis-sakha-slm repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does tabis sakha slm use?
Hugging Face lists the license as apache-2.0. 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 Tabis on an 8 GB GPU?
Yes, the 0.53 GB GGUF file uses about 1.4 GB of RAM at 8 k context, fitting comfortably on 8 GB VRAM.
Does Tabis support vision tasks?
Tabis is a text‑only model; it does not provide vision inference capabilities.
What languages does Tabis understand?
Tabis is adapted for Yakut (Sakha) and Russian, with bilingual translation support.