llama sahabat AI v2 70B GGUF Relist needs about 34.1 GB of memory at Q3_K_S (a 30.9 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 3 quants, from 24.5 GB (Q2_K_S) to 75.0 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.
llama sahabat AI v2 70B GGUF Relist is a 70.6B-parameter Llama model in GGUF format, quantized by blackshell69. Its trained context length is 128K tokens. The repository has 3 quant files, from 24.5 GB (Q2_K_S) to 75.0 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K_S | 24.5 GB | 27.7 GB | Too big | Get file → | |
| Q3_K_S | 30.9 GB | 34.1 GB | Too big | Get file → | |
| Q8_0 | 75.0 GB | 78.2 GB | Too big | Get file → |
What GPU do you need for llama sahabat AI v2 70B GGUF Relist?
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: the best quant that fits is Q2_K_S (24.5 GB file, about 27.7 GB in use).
- 48 GB VRAM: the best quant that fits is Q3_K_S (30.9 GB file, about 34.1 GB in use).
Which llama sahabat AI v2 70B GGUF Relist quant should you choose?
Q3_K_S (30.9 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
If memory is tight, the smallest file is Q2_K_S at 24.5 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 llama sahabat AI v2 70B GGUF Relist
How much VRAM does llama sahabat AI v2 70B GGUF Relist need?
About 34.1 GB at Q3_K_S with an 8K context window. That is the 30.9 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 llama sahabat AI v2 70B GGUF Relist on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 27.7 GB, so you would need a larger GPU or CPU offloading.
What is the file size of llama sahabat AI v2 70B GGUF Relist GGUF?
It depends on the quant: Q2_K_S is 24.5 GB, Q3_K_S is 30.9 GB, Q8_0 is 75.0 GB.
What context length does llama sahabat AI v2 70B GGUF Relist support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 2.7 GB at 8K and 10.7 GB at 32K.
Where can I download llama sahabat AI v2 70B GGUF Relist GGUF?
The files are on Hugging Face in the blackshell69/llama-sahabat-AI-v2-70B-GGUF-Relist repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does llama sahabat AI v2 70B GGUF Relist use?
Hugging Face lists the license as llama3.1. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.