PLLuM 8x7B nc instruct needs about 14.1 GB of memory at TQ2_0 (a 12.5 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 3 quants, from 10.3 GB (TQ1_0) to 49.6 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
PLLuM 8x7B nc instruct is a 46.7B-parameter Pllum model in GGUF format, quantized by piotreknow02. Its trained context length is 32K tokens. The repository has 3 quant files, from 10.3 GB (TQ1_0) to 49.6 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| TQ1_0 | 10.3 GB | 11.9 GB | Too big | Get file → | |
| TQ2_0 | 12.5 GB | 14.1 GB | Too big | Get file → | |
| Q8_0 | 49.6 GB | 51.2 GB | Too big | Get file → |
What GPU do you need for PLLuM 8x7B nc 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: the best quant that fits is TQ1_0 (10.3 GB file, about 11.9 GB in use).
- 16 GB VRAM: the best quant that fits is TQ2_0 (12.5 GB file, about 14.1 GB in use).
- 24 GB VRAM: the best quant that fits is TQ2_0 (12.5 GB file, about 14.1 GB in use).
- 32 GB VRAM: the best quant that fits is TQ2_0 (12.5 GB file, about 14.1 GB in use).
- 48 GB VRAM: the best quant that fits is TQ2_0 (12.5 GB file, about 14.1 GB in use).
Which PLLuM 8x7B nc instruct quant should you choose?
TQ2_0 (12.5 GB) is the middle option in this repository. Lower bit counts mean smaller files and more quality loss.
If memory is tight, the smallest file is TQ1_0 at 10.3 GB, with the quality trade-offs that come with fewer bits. Lower bit counts mean smaller files and more quality loss.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about PLLuM 8x7B nc instruct
How much VRAM does PLLuM 8x7B nc instruct need?
About 14.1 GB at TQ2_0 with an 8K context window. That is the 12.5 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 PLLuM 8x7B nc instruct on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 11.9 GB, so you would need a larger GPU or CPU offloading.
What is the file size of PLLuM 8x7B nc instruct GGUF?
It depends on the quant: TQ1_0 is 10.3 GB, TQ2_0 is 12.5 GB, Q8_0 is 49.6 GB.
What context length does PLLuM 8x7B nc instruct 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 PLLuM 8x7B nc instruct GGUF?
The files are on Hugging Face in the piotreknow02/PLLuM-8x7B-nc-instruct-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 PLLuM 8x7B nc instruct use?
Hugging Face lists the license as cc-by-nc-4.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.