Llama 3.1 SuperSwallow 70B Instruct v0.1 needs about 144.3 GB of memory at BF16 (a 141.1 GB file) with an 8K context window, which is more than a 48 GB GPU holds. Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.
Llama 3.1 SuperSwallow 70B Instruct v0.1 is a 70.6B-parameter Llama model in GGUF format, quantized by jeanvit. Its trained context length is 128K tokens. The repository has 1 quant file, from 141.1 GB (BF16) to 141.1 GB (BF16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| BF16 | 141.1 GB (4 parts) | 144.3 GB | Too big | Get file → |
What GPU do you need for Llama 3.1 SuperSwallow 70B Instruct v0.1?
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: no quant fits at an 8K context.
Which Llama 3.1 SuperSwallow 70B Instruct v0.1 quant should you choose?
BF16 (141.1 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Llama 3.1 SuperSwallow 70B Instruct v0.1
How much VRAM does Llama 3.1 SuperSwallow 70B Instruct v0.1 need?
About 144.3 GB at BF16 with an 8K context window. That is the 141.1 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 3.1 SuperSwallow 70B Instruct v0.1 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 144.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Llama 3.1 SuperSwallow 70B Instruct v0.1 GGUF?
It depends on the quant: BF16 is 141.1 GB.
What context length does Llama 3.1 SuperSwallow 70B Instruct v0.1 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 3.1 SuperSwallow 70B Instruct v0.1 GGUF?
The files are on Hugging Face in the jeanvit/Llama-3.1-SuperSwallow-70B-Instruct-v0.1-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 Llama 3.1 SuperSwallow 70B Instruct v0.1 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.