NeMoe needs about 24.2 GB of memory at Q8_0 (a 22.4 GB file) with an 8K context window, so it fits on a 32 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.
NeMoe is a 21.1B-parameter Nemoe model in GGUF format, quantized by Undi95. Its trained context length is 1000K tokens. The repository has 1 quant file, from 22.4 GB (Q8_0) to 22.4 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 22.4 GB | 24.2 GB | Too big | Get file → |
What GPU do you need for NeMoe?
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: 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 Q8_0 (22.4 GB file, about 24.2 GB in use).
Which NeMoe quant should you choose?
Q8_0 (22.4 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about NeMoe
How much VRAM does NeMoe need?
About 24.2 GB at Q8_0 with an 8K context window. That is the 22.4 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 NeMoe on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 24.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of NeMoe GGUF?
It depends on the quant: Q8_0 is 22.4 GB.
What context length does NeMoe support?
The GGUF header lists a trained context length of 1,024,000 tokens (1000K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.
Where can I download NeMoe GGUF?
The files are on Hugging Face in the Undi95/NeMoe-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.