unsloth Llama 3.1 Nemotron 70B Instruct needs about 38.9 GB of memory at Q3_K (a 34.3 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 13 quants, from 26.2 GB (Q4_0) to 42.5 GB (Q4_K).
unsloth Llama 3.1 Nemotron 70B Instruct is a 70.6B-parameter Llama model in GGUF format, quantized by RichardErkhov. Its trained context length is 128K tokens. The repository has 13 quant files, from 26.2 GB (Q4_0) to 42.5 GB (Q4_K).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_0 | 26.2 GB | 29.9 GB | Too big | Get file → | |
| Q2_K | 26.4 GB | 30.0 GB | Too big | Get file → | |
| IQ3_XS | 29.3 GB | 33.3 GB | Too big | Get file → | |
| IQ3_S | 30.9 GB | 35.1 GB | Too big | Get file → | |
| Q3_K_S | 30.9 GB | 35.1 GB | Too big | Get file → | |
| IQ3_M | 31.9 GB | 36.3 GB | Too big | Get file → | |
| Q3_K | 34.3 GB | 38.9 GB | Too big | Get file → | |
| Q3_K_M | 34.3 GB | 38.9 GB | Too big | Get file → | |
| Q3_K_L | 37.1 GB | 42.1 GB | Too big | Get file → | |
| IQ4_XS | 38.3 GB | 43.4 GB | Too big | Get file → | |
| IQ4_NL | 40.3 GB (2 parts) | 45.7 GB | Too big | Get file → | |
| Q4_K_S | 40.3 GB (2 parts) | 45.7 GB | Too big | Get file → | |
| Q4_K | 42.5 GB (2 parts) | 48.1 GB | Too big | Get file → |
What GPU do you need for unsloth Llama 3.1 Nemotron 70B Instruct?
These figures add the file size, an fp16 KV cache at an 8K context window 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 30.0 GB in use).
- 48 GB VRAM: the best quant that fits is IQ4_NL (40.3 GB file, about 45.7 GB in use).
Which unsloth Llama 3.1 Nemotron 70B Instruct quant should you choose?
Q3_K (34.3 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 Q4_0 at 26.2 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about unsloth Llama 3.1 Nemotron 70B Instruct
How much VRAM does unsloth Llama 3.1 Nemotron 70B Instruct need?
About 38.9 GB at Q3_K with an 8K context window. That is the 34.3 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 unsloth Llama 3.1 Nemotron 70B Instruct on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 29.9 GB, so you would need a larger GPU or CPU offloading.
What is the file size of unsloth Llama 3.1 Nemotron 70B Instruct GGUF?
It depends on the quant: Q4_0 is 26.2 GB, Q2_K is 26.4 GB, IQ3_XS is 29.3 GB, IQ3_S is 30.9 GB, Q3_K_S is 30.9 GB, IQ3_M is 31.9 GB and 7 more.
What context length does unsloth Llama 3.1 Nemotron 70B Instruct support?
The GGUF header lists a trained context length of 131,072 tokens (128K).
Where can I download unsloth Llama 3.1 Nemotron 70B Instruct GGUF?
The files are on Hugging Face in the RichardErkhov/unsloth_-_Llama-3.1-Nemotron-70B-Instruct-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.