LFM2.5 1.2B Saiga It v3 needs about 2.3 GB of memory at Q4_K_M (a 0.7 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 25 quants, from 0.0 GB to 1.0 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
LFM2.5 1.2B Saiga It v3 – Russian language LLM
LFM2.5 1.2B Saiga It v3 is a 1.17 billion parameter model trained on expanded Russian datasets. It supports tool usage and is available in multiple GGUF quantizations. The model is designed for research and creative Russian language generation.
Good at
- Russian text generation
- Tool‑based interactions
- Creative content
Limits
- Hallucinates on factual queries
- No vision support
- Requires 8 k context for estimates
Best for
- Russian creative writing
- Research experiments
- Tool‑enabled dialogue
Who it’s for. Researchers and developers needing a lightweight Russian LLM for experimentation. The model is suitable for creative tasks but not for reliable factual or professional use.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.6 GB | Fits | Get file → | |
| IQ1_S | 0.3 GB | 1.9 GB | Fits | Get file → | |
| IQ1_M | 0.3 GB | 1.9 GB | Fits | Get file → | |
| IQ2_XXS | 0.4 GB | 1.9 GB | Fits | Get file → | |
| IQ2_XS | 0.4 GB | 2.0 GB | Fits | Get file → | |
| IQ2_S | 0.4 GB | 2.0 GB | Fits | Get file → | |
| IQ2_M | 0.4 GB | 2.0 GB | Fits | Get file → | |
| Q2_K_S | 0.5 GB | 2.0 GB | Fits | Get file → | |
| Q2_K | 0.5 GB | 2.1 GB | Fits | Get file → | |
| IQ3_XXS | 0.5 GB | 2.1 GB | Fits | Get file → | |
| IQ3_XS | 0.5 GB | 2.1 GB | Fits | Get file → | |
| IQ3_S | 0.6 GB | 2.1 GB | Fits | Get file → | |
| Q3_K_S | 0.6 GB | 2.1 GB | Fits | Get file → | |
| IQ3_M | 0.6 GB | 2.1 GB | Fits | Get file → | |
| Q3_K_M | 0.6 GB | 2.2 GB | Fits | Get file → | |
| Q3_K_L | 0.6 GB | 2.2 GB | Fits | Get file → | |
| IQ4_XS | 0.7 GB | 2.2 GB | Fits | Get file → | |
| IQ4_NL | 0.7 GB | 2.3 GB | Fits | Get file → | |
| Q4_0 | 0.7 GB | 2.3 GB | Fits | Get file → | |
| Q4_K_S | 0.7 GB | 2.3 GB | Fits | Get file → | |
| Q4_K_M | 0.7 GB | 2.3 GB | Fits | Get file → | |
| Q4_1 | 0.8 GB | 2.3 GB | Fits | Get file → | |
| Q5_K_S | 0.8 GB | 2.4 GB | Fits | Get file → | |
| Q5_K_M | 0.8 GB | 2.4 GB | Fits | Get file → | |
| Q6_K | 1.0 GB | 2.5 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_0 (0.7 GB) or Q4_K_S (0.7 GB). For 4 GB VRAM, use IQ1_S (0.3 GB) or IQ1_M (0.33 GB). Larger VRAM allows higher‑quality quants such as Q5_K_M (0.84 GB). Memory estimates are approximate.
What GPU do you need for LFM2.5 1.2B Saiga It v3?
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 Q6_K (1.0 GB file, about 2.5 GB in use).
Which LFM2.5 1.2B Saiga It v3 quant should you choose?
Q4_K_M is the usual starting point for LFM2.5 1.2B Saiga It v3: it balances file size and quality well. Here it is a 0.7 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 LFM2.5 1.2B Saiga It v3
How much VRAM does LFM2.5 1.2B Saiga It v3 need?
About 2.3 GB at Q4_K_M with an 8K context window. That is the 0.7 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 LFM2.5 1.2B Saiga It v3 on an 8 GB GPU?
Yes, with Q6_K: the 1.0 GB file needs about 2.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of LFM2.5 1.2B Saiga It v3 GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 0.3 GB, IQ1_M is 0.3 GB, IQ2_XXS is 0.4 GB, IQ2_XS is 0.4 GB, IQ2_S is 0.4 GB and 19 more.
What context length does LFM2.5 1.2B Saiga It v3 support?
The GGUF header lists a trained context length of 128,000 tokens (125K). 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 LFM2.5 1.2B Saiga It v3 GGUF?
The files are on Hugging Face in the mradermacher/LFM2.5-1.2B-Saiga-It-v3-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 LFM2.5 1.2B Saiga It v3 use?
Hugging Face lists the license as other. 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, quantizations such as Q4_0 or Q4_K_S fit within 8 GB VRAM with an estimated 2.3 GB memory usage at 8 k context.
Does this model support vision?
No, the model has no vision capabilities.
What context length does it support?
The model was trained with a context length of 128 000 tokens.