NatureLM 8x7B Inst needs about 30.1 GB of memory at Q4_K_M (a 28.5 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 25 quants, from 9.8 GB (IQ1_S) to 93.5 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
NatureLM 8x7B Inst is a 46.8B-parameter Naturelm model in GGUF format, quantized by gabriellarson. Its trained context length is 32K tokens. The repository has 25 quant files, from 9.8 GB (IQ1_S) to 93.5 GB (F16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 9.8 GB | 11.4 GB | Too big | Get file → | |
| IQ1_M | 10.9 GB | 12.4 GB | Too big | Get file → | |
| IQ2_XXS | 12.6 GB | 14.2 GB | Too big | Get file → | |
| IQ2_XS | 13.9 GB | 15.5 GB | Too big | Get file → | |
| IQ2_S | 14.2 GB | 15.7 GB | Too big | Get file → | |
| IQ2_M | 15.5 GB | 17.1 GB | Too big | Get file → | |
| Q2_K_S | 16.1 GB | 17.6 GB | Too big | Get file → | |
| Q2_K | 17.3 GB | 18.9 GB | Too big | Get file → | |
| IQ3_XXS | 18.3 GB | 19.8 GB | Too big | Get file → | |
| IQ3_XS | 19.4 GB | 21.0 GB | Too big | Get file → | |
| IQ3_S | 20.5 GB | 22.0 GB | Too big | Get file → | |
| Q3_K_S | 20.5 GB | 22.0 GB | Too big | Get file → | |
| IQ3_M | 21.5 GB | 23.0 GB | Too big | Get file → | |
| Q3_K_M | 22.6 GB | 24.2 GB | Too big | Get file → | |
| Q3_K_L | 24.2 GB | 25.8 GB | Too big | Get file → | |
| IQ4_XS | 25.1 GB | 26.7 GB | Too big | Get file → | |
| Q4_0 | 26.6 GB | 28.2 GB | Too big | Get file → | |
| Q4_K_S | 26.8 GB | 28.4 GB | Too big | Get file → | |
| Q4_K_M | 28.5 GB | 30.1 GB | Too big | Get file → | |
| Q5_K_S | 32.3 GB | 33.8 GB | Too big | Get file → | |
| Q5_0 | 32.4 GB | 34.0 GB | Too big | Get file → | |
| Q5_K_M | 33.3 GB | 34.8 GB | Too big | Get file → | |
| Q6_K | 38.4 GB | 40.0 GB | Too big | Get file → | |
| Q8_0 | 49.7 GB | 51.3 GB | Too big | Get file → | |
| F16 | 93.5 GB | 95.1 GB | Too big | Get file → |
What GPU do you need for NatureLM 8x7B Inst?
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: the best quant that fits is IQ1_S (9.8 GB file, about 11.4 GB in use).
- 16 GB VRAM: the best quant that fits is IQ2_S (14.2 GB file, about 15.7 GB in use).
- 24 GB VRAM: the best quant that fits is IQ3_M (21.5 GB file, about 23.0 GB in use).
- 32 GB VRAM: the best quant that fits is Q4_K_M (28.5 GB file, about 30.1 GB in use).
- 48 GB VRAM: the best quant that fits is Q6_K (38.4 GB file, about 40.0 GB in use).
Which NatureLM 8x7B Inst quant should you choose?
Q4_K_M is the usual starting point for NatureLM 8x7B Inst: it balances file size and quality well. Here it is a 28.5 GB file.
The Q8_0 file is 49.7 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is IQ1_S at 9.8 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 NatureLM 8x7B Inst
How much VRAM does NatureLM 8x7B Inst need?
About 30.1 GB at Q4_K_M with an 8K context window. That is the 28.5 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 NatureLM 8x7B Inst on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 11.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of NatureLM 8x7B Inst GGUF?
It depends on the quant: IQ1_S is 9.8 GB, IQ1_M is 10.9 GB, IQ2_XXS is 12.6 GB, IQ2_XS is 13.9 GB, IQ2_S is 14.2 GB, IQ2_M is 15.5 GB and 19 more.
What context length does NatureLM 8x7B Inst support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.
Where can I download NatureLM 8x7B Inst GGUF?
The files are on Hugging Face in the gabriellarson/NatureLM-8x7B-Inst-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 NatureLM 8x7B Inst use?
Hugging Face lists the license as mit. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.