YandexGPT 5 Lite 8B pretrain needs about 5.8 GB of memory at IQ4_NL (a 4.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 23 quants, from 0.6 GB (IQ2_M) to 32.1 GB.
YandexGPT 5 Lite 8B pretrain is a 8.04B-parameter Yandexgpt model in GGUF format, quantized by yaroslav0530. Its trained context length is 32K tokens. The repository has 23 quant files, from 0.6 GB (IQ2_M) to 32.1 GB.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_M | 0.6 GB | 1.2 GB | Fits | Get file → | |
| IQ3_XXS | 0.6 GB | 1.2 GB | Fits | Get file → | |
| TQ1_0 | 2.2 GB | 3.0 GB | Fits | Get file → | |
| TQ2_0 | 2.5 GB | 3.3 GB | Fits | Get file → | |
| Q2_K | 3.2 GB | 4.1 GB | Fits | Get file → | |
| Q3_K_S | 3.7 GB | 4.6 GB | Fits | Get file → | |
| Q3_K | 4.0 GB | 5.0 GB | Fits | Get file → | |
| Q3_K_L | 4.3 GB | 5.3 GB | Fits | Get file → | |
| IQ4_XS | 4.5 GB | 5.5 GB | Fits | Get file → | |
| Q4_0 | 4.7 GB | 5.7 GB | Fits | Get file → | |
| Q4_K_S | 4.7 GB | 5.8 GB | Fits | Get file → | |
| IQ4_NL | 4.7 GB | 5.8 GB | Fits | Get file → | |
| Q4_K | 4.9 GB | 6.0 GB | Fits | Get file → | |
| Q4_1 | 5.1 GB | 6.2 GB | Fits | Get file → | |
| Q5_0 | 5.6 GB | 6.8 GB | Fits | Get file → | |
| Q5_K_S | 5.6 GB | 6.8 GB | Fits | Get file → | |
| Q5_K | 5.7 GB | 6.9 GB | Fits | Get file → | |
| Q5_1 | 6.1 GB | 7.3 GB | Tight | Get file → | |
| Q6_K | 6.6 GB | 7.9 GB | Tight | Get file → | |
| Q8_0 | 8.5 GB | 10.1 GB | Too big | Get file → | |
| BF16 | 16.1 GB | 18.5 GB | Too big | Get file → | |
| — | 16.1 GB | 18.5 GB | Too big | Get file → | |
| — | 32.1 GB | 36.5 GB | Too big | Get file → |
What GPU do you need for YandexGPT 5 Lite 8B pretrain?
These figures add the file size, an fp16 KV cache at an 8K context window 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 TQ2_0 (2.5 GB file, about 3.3 GB in use).
- 6 GB VRAM: the best quant that fits is Q4_K (4.9 GB file, about 6.0 GB in use).
- 8 GB VRAM: the best quant that fits is Q6_K (6.6 GB file, about 7.9 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (8.5 GB file, about 10.1 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (8.5 GB file, about 10.1 GB in use).
- 24 GB VRAM: the best quant that fits is BF16 (16.1 GB file, about 18.5 GB in use).
- 32 GB VRAM: the best quant that fits is BF16 (16.1 GB file, about 18.5 GB in use).
- 48 GB VRAM: the best quant that fits is the main file (32.1 GB file, about 36.5 GB in use).
Which YandexGPT 5 Lite 8B pretrain quant should you choose?
IQ4_NL (4.7 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
If memory is tight, the smallest file is IQ2_M at 0.6 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
Source
Frequently asked questions about YandexGPT 5 Lite 8B pretrain
How much VRAM does YandexGPT 5 Lite 8B pretrain need?
About 5.8 GB at IQ4_NL with an 8K context window. That is the 4.7 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 YandexGPT 5 Lite 8B pretrain on an 8 GB GPU?
Yes, with Q6_K: the 6.6 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of YandexGPT 5 Lite 8B pretrain GGUF?
It depends on the quant: IQ2_M is 0.6 GB, IQ3_XXS is 0.6 GB, TQ1_0 is 2.2 GB, TQ2_0 is 2.5 GB, Q2_K is 3.2 GB, Q3_K_S is 3.7 GB and 17 more.
What context length does YandexGPT 5 Lite 8B pretrain support?
The GGUF header lists a trained context length of 32,768 tokens (32K).
Where can I download YandexGPT 5 Lite 8B pretrain GGUF?
The files are on Hugging Face in the yaroslav0530/YandexGPT-5-Lite-8B-pretrain-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 YandexGPT 5 Lite 8B pretrain 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.