NurseButtercup 4x7B bf16 i1 needs about 13.2 GB of memory at BF16 (a 11.6 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 5 quants, from 8.8 GB (BF16) to 14.6 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
NurseButtercup 4x7B bf16 i1 is a 24.2B-parameter Nursebuttercup model in GGUF format, quantized by mradermacher. Its trained context length is 32K tokens. The repository has 5 quant files, from 8.8 GB (BF16) to 14.6 GB (BF16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| BF16 | 8.8 GB | 10.4 GB | Too big | Get file → | |
| BF16 | 9.3 GB | 10.9 GB | Too big | Get file → | |
| BF16 | 11.6 GB | 13.2 GB | Too big | Get file → | |
| BF16 | 13.7 GB | 15.3 GB | Too big | Get file → | |
| BF16 | 14.6 GB | 16.2 GB | Too big | Get file → |
What GPU do you need for NurseButtercup 4x7B bf16 i1?
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 BF16 (9.3 GB file, about 10.9 GB in use).
- 16 GB VRAM: the best quant that fits is BF16 (13.7 GB file, about 15.3 GB in use).
- 24 GB VRAM: the best quant that fits is BF16 (14.6 GB file, about 16.2 GB in use).
Which NurseButtercup 4x7B bf16 i1 quant should you choose?
BF16 (11.6 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
If memory is tight, the smallest file is BF16 at 8.8 GB, with the quality trade-offs that come with fewer bits. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about NurseButtercup 4x7B bf16 i1
How much VRAM does NurseButtercup 4x7B bf16 i1 need?
About 13.2 GB at BF16 with an 8K context window. That is the 11.6 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 NurseButtercup 4x7B bf16 i1 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 10.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of NurseButtercup 4x7B bf16 i1 GGUF?
It depends on the quant: BF16 is 8.8 GB, BF16 is 9.3 GB, BF16 is 11.6 GB, BF16 is 13.7 GB, BF16 is 14.6 GB.
What context length does NurseButtercup 4x7B bf16 i1 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 NurseButtercup 4x7B bf16 i1 GGUF?
The files are on Hugging Face in the mradermacher/NurseButtercup-4x7B-bf16-i1-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 NurseButtercup 4x7B bf16 i1 use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.