SA

Saiga_Yandexgpt_8B_Sft_M4_D19_Hf

SaigaGGUF by IlyaGusevUpdated 2025-03-13
Download on Hugging Face
Parameters8B
Context32K
Layers32
Architecturellama
Smallest quant3.2 GB
Quick answer

Saiga_Yandexgpt_8B_Sft_M4_D19_Hf needs about 6.5 GB of memory at Q4_K_M (a 4.9 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 11 quants, from 3.2 GB (Q2_K) to 16.1 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Saiga YandexGPT 8B – Llama‑based model with 32k context

Saiga YandexGPT 8B is a 8B‑parameter Llama architecture model trained with a 32,768 token context window. It is available in multiple GGUF quantizations for efficient inference on a range of hardware.

Good at

  • Large context handling
  • Efficient inference with low‑bit quantization
  • Compatibility with llama.cpp

Limits

  • No vision support
  • License type unspecified
  • Requires at least 9 GB RAM for q8_0

Best for

  • Chat applications needing long context
  • Fine‑tuning on custom data
  • Running on consumer GPUs with limited VRAM

Who it’s for. Developers and researchers who need a 32k context Llama model and can work with GGUF files. The model is suitable for local deployment on systems with moderate memory resources.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K3.2 GB 4.8 GB
Fits Get file →
Q3_K_S3.7 GB 5.2 GB
Fits Get file →
Q3_K_M4.0 GB 5.6 GB
Fits Get file →
Q4_04.7 GB 6.2 GB
Fits Get file →
Q4_K_S4.7 GB 6.3 GB
Fits Get file →
Q4_K_M4.9 GB 6.5 GB
Fits Get file →
Q5_K_S5.6 GB 7.2 GB
Fits Get file →
Q5_K_M5.7 GB 7.3 GB
Tight Get file →
Q6_K6.6 GB 8.2 GB
Too big Get file →
Q8_08.5 GB 10.1 GB
Too big Get file →
BF1616.1 GB 17.7 GB
Too big Get file →

For 8 GB VRAM use Q4_K_M (4.93 GB file, ~6.5 GB memory). For 6 GB VRAM use Q3_K_M (4.02 GB file, ~5.6 GB memory). For 4 GB VRAM use Q2_K (3.18 GB file, ~4.8 GB memory). Estimates are approximate.

What GPU do you need for Saiga_Yandexgpt_8B_Sft_M4_D19_Hf?

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: the best quant that fits is Q3_K_M (4.0 GB file, about 5.6 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_M (5.7 GB file, about 7.3 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 17.7 GB in use).

Which Saiga_Yandexgpt_8B_Sft_M4_D19_Hf quant should you choose?

Q4_K_M is the usual starting point for Saiga_Yandexgpt_8B_Sft_M4_D19_Hf: it balances file size and quality well. Here it is a 4.9 GB file.

The Q8_0 file is 8.5 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q2_K at 3.2 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

Architecturellama
Parameters8B
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized byIlyaGusev
FamilySaiga
Licenseother
Downloads (HF)3,264
Last updated2025-03-13

Frequently asked questions about Saiga_Yandexgpt_8B_Sft_M4_D19_Hf

How much VRAM does Saiga_Yandexgpt_8B_Sft_M4_D19_Hf need?

About 6.5 GB at Q4_K_M with an 8K context window. That is the 4.9 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 Saiga_Yandexgpt_8B_Sft_M4_D19_Hf on an 8 GB GPU?

Yes, with Q5_K_M: the 5.7 GB file needs about 7.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Saiga_Yandexgpt_8B_Sft_M4_D19_Hf GGUF?

It depends on the quant: Q2_K is 3.2 GB, Q3_K_S is 3.7 GB, Q3_K_M is 4.0 GB, Q4_0 is 4.7 GB, Q4_K_S is 4.7 GB, Q4_K_M is 4.9 GB and 5 more.

What context length does Saiga_Yandexgpt_8B_Sft_M4_D19_Hf support?

The GGUF header lists a trained context length of 32,768 tokens (32K). 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 Saiga_Yandexgpt_8B_Sft_M4_D19_Hf GGUF?

The files are on Hugging Face in the IlyaGusev/saiga_yandexgpt_8b_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 Saiga_Yandexgpt_8B_Sft_M4_D19_Hf 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, using Q4_K_M or Q3_K_M quantizations will fit within 8 GB VRAM with some headroom.

Does the model support vision tasks?

No, the model has no vision capabilities.

What is the context length of this model?

The model supports a 32,768 token context window.

Similar models

Browse all →

More from IlyaGusev

All by IlyaGusev →

More Saiga models

All Saiga →

Other small models

All small models →