Llama 3_1 Nemotron 51B Instruct Abliterated needs about 35.3 GB of memory at Q4_K_M (a 31.0 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 10 quants, from 19.4 GB (Q2_K) to 42.3 GB (Q6_K).
Llama 3_1 Nemotron 51B Instruct Abliterated is a 51.5B-parameter Llama model in GGUF format, quantized by mradermacher. Its trained context length is 128K tokens. The repository has 10 quant files, from 19.4 GB (Q2_K) to 42.3 GB (Q6_K).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 19.4 GB | 22.2 GB | Too big | Get file → | |
| Q3_K_S | 22.7 GB | 25.9 GB | Too big | Get file → | |
| Q3_K_M | 25.2 GB | 28.7 GB | Too big | Get file → | |
| Q3_K_L | 27.3 GB | 31.1 GB | Too big | Get file → | |
| IQ4_XS | 28.0 GB | 31.8 GB | Too big | Get file → | |
| Q4_K_S | 29.5 GB | 33.5 GB | Too big | Get file → | |
| Q4_K_M | 31.0 GB | 35.3 GB | Too big | Get file → | |
| Q5_K_S | 35.6 GB | 40.3 GB | Too big | Get file → | |
| Q5_K_M | 36.5 GB | 41.3 GB | Too big | Get file → | |
| Q6_K | 42.3 GB | 47.8 GB | Too big | Get file → |
What GPU do you need for Llama 3_1 Nemotron 51B Instruct Abliterated?
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: the best quant that fits is Q2_K (19.4 GB file, about 22.2 GB in use).
- 32 GB VRAM: the best quant that fits is IQ4_XS (28.0 GB file, about 31.8 GB in use).
- 48 GB VRAM: the best quant that fits is Q6_K (42.3 GB file, about 47.8 GB in use).
Which Llama 3_1 Nemotron 51B Instruct Abliterated quant should you choose?
Q4_K_M is the usual starting point for Llama 3_1 Nemotron 51B Instruct Abliterated: it balances file size and quality well. Here it is a 31.0 GB file.
If memory is tight, the smallest file is Q2_K at 19.4 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 Llama 3_1 Nemotron 51B Instruct Abliterated
How much VRAM does Llama 3_1 Nemotron 51B Instruct Abliterated need?
About 35.3 GB at Q4_K_M with an 8K context window. That is the 31.0 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 Nemotron 51B Instruct Abliterated on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 22.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Llama 3_1 Nemotron 51B Instruct Abliterated GGUF?
It depends on the quant: Q2_K is 19.4 GB, Q3_K_S is 22.7 GB, Q3_K_M is 25.2 GB, Q3_K_L is 27.3 GB, IQ4_XS is 28.0 GB, Q4_K_S is 29.5 GB and 4 more.
What context length does Llama 3_1 Nemotron 51B Instruct Abliterated support?
The GGUF header lists a trained context length of 131,072 tokens (128K).
Where can I download Llama 3_1 Nemotron 51B Instruct Abliterated GGUF?
The files are on Hugging Face in the mradermacher/Llama-3_1-Nemotron-51B-Instruct-abliterated-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 Nemotron 51B Instruct Abliterated use?
Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.