NemoRemix 12B needs about 14.9 GB of memory at Q8_0 (a 13.0 GB file) with an 8K context window, so it fits on a 16 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.
NemoRemix 12B is a 12.2B-parameter Nemoremix model in GGUF format, quantized by MarinaraSpaghetti. Its trained context length is 1000K tokens. The repository has 1 quant file, from 13.0 GB (Q8_0) to 13.0 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 13.0 GB | 14.9 GB | Too big | Get file → |
What GPU do you need for NemoRemix 12B?
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: the best quant that fits is Q8_0 (13.0 GB file, about 14.9 GB in use).
Which NemoRemix 12B quant should you choose?
Q8_0 (13.0 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
Source
Frequently asked questions about NemoRemix 12B
How much VRAM does NemoRemix 12B need?
About 14.9 GB at Q8_0 with an 8K context window. That is the 13.0 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 NemoRemix 12B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 14.9 GB, so you would need a larger GPU or CPU offloading.
What is the file size of NemoRemix 12B GGUF?
It depends on the quant: Q8_0 is 13.0 GB.
What context length does NemoRemix 12B 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 NemoRemix 12B GGUF?
The files are on Hugging Face in the MarinaraSpaghetti/NemoRemix-12B-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.