saiga2 70b needs about 32.5 GB of memory at Q2_K (a 29.3 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 2 quants, from 29.3 GB (Q2_K) to 43.2 GB (Q4_1).
saiga2 70b is a 69B-parameter Saiga model in GGUF format, quantized by IlyaGusev. Its trained context length is 4K tokens. The repository has 2 quant files, from 29.3 GB (Q2_K) to 43.2 GB (Q4_1).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 29.3 GB | 31.1 GB | Too big | Get file → | |
| Q4_1 | 43.2 GB | 45.0 GB | Too big | Get file → |
What GPU do you need for saiga2 70b?
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: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: no quant fits at an 8K context.
- 32 GB VRAM: no quant fits at an 8K context.
- 48 GB VRAM: the best quant that fits is Q4_1 (43.2 GB file, about 46.4 GB in use).
Which saiga2 70b quant should you choose?
Q2_K (29.3 GB) is the middle option in this repository. 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 saiga2 70b
How much VRAM does saiga2 70b need?
About 32.5 GB at Q2_K with an 8K context window. That is the 29.3 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 saiga2 70b on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 32.5 GB, so you would need a larger GPU or CPU offloading.
What is the file size of saiga2 70b GGUF?
It depends on the quant: Q2_K is 29.3 GB, Q4_1 is 43.2 GB.
What context length does saiga2 70b support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 2.7 GB at 8K and 1.3 GB at 4K.
Where can I download saiga2 70b GGUF?
The files are on Hugging Face in the IlyaGusev/saiga2_70b_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 saiga2 70b use?
Hugging Face lists the license as llama2. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.