Smaug-Llama-3-70B-Instruct 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 26.4 GB (Q2_K) to 40.3 GB (Q4_K_S).
Smaug-Llama-3-70B-Instruct is a 70.6B-parameter Llama model in GGUF format, quantized by redponike. Its trained context length is 8K tokens. The repository has 3 quant files, from 26.4 GB (Q2_K) to 40.3 GB (Q4_K_S).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 26.4 GB | 29.6 GB | Too big | Get file → | |
| Q3_K_S | 30.9 GB | 34.1 GB | Too big | Get file → | |
| Q4_K_S | 40.3 GB | 43.5 GB | Too big | Get file → |
What GPU do you need for Smaug-Llama-3-70B-Instruct?
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 (26.4 GB file, about 29.6 GB in use).
- 48 GB VRAM: the best quant that fits is Q4_K_S (40.3 GB file, about 43.5 GB in use).
Which Smaug-Llama-3-70B-Instruct 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 at 26.4 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
Frequently asked questions about Smaug-Llama-3-70B-Instruct
How much VRAM does Smaug-Llama-3-70B-Instruct 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 Smaug-Llama-3-70B-Instruct on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 29.6 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Smaug-Llama-3-70B-Instruct GGUF?
It depends on the quant: Q2_K is 26.4 GB, Q3_K_S is 30.9 GB, Q4_K_S is 40.3 GB.
What context length does Smaug-Llama-3-70B-Instruct support?
The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 2.7 GB at 8K and 2.7 GB at 8K.
Where can I download Smaug-Llama-3-70B-Instruct GGUF?
The files are on Hugging Face in the redponike/Smaug-Llama-3-70B-Instruct-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.