NE

NemoReRemix

NemoreremixGGUF by MarinaraSpaghettiUpdated 2024-08-15
Download on Hugging Face
Parameters12.2B
Context1000K
Layers40
Architecturellama
Smallest quant13.0 GB
Quick answer

NemoReRemix 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.

NemoReRemix is a 12.2B-parameter Nemoreremix 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

QuantFileEst. memoryvs VRAMResultDownload
Q8_013.0 GB 14.9 GB
Too big Get file →

What GPU do you need for NemoReRemix?

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 NemoReRemix 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

Architecturellama
Parameters12.2B
Layers40
Trained context1,024,000 tokens
KV cache (fp16)160 KB per token

Source

Quantized byMarinaraSpaghetti
Downloads (HF)6
Last updated2024-08-15

Frequently asked questions about NemoReRemix

How much VRAM does NemoReRemix 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 NemoReRemix 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 NemoReRemix GGUF?

It depends on the quant: Q8_0 is 13.0 GB.

What context length does NemoReRemix 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 NemoReRemix GGUF?

The files are on Hugging Face in the MarinaraSpaghetti/NemoReRemix-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from MarinaraSpaghetti

All by MarinaraSpaghetti →

More Nemoreremix models

All Nemoreremix →

Other medium models

All medium models →