MI

mistral nemo gec

MistralGGUF by culverscrupleUpdated 2024-09-26
Download on Hugging Face
Parameters12.2B
Context1000K
Layers40
Architecturellama
Smallest quant7.5 GB
Quick answer

mistral nemo gec needs about 9.3 GB of memory at Q4_K_M (a 7.5 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 3 quants, from 7.5 GB (Q4_K_M) to 24.5 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

mistral nemo gec is a 12.2B-parameter Mistral model in GGUF format, quantized by culverscruple. Its trained context length is 1000K tokens. The repository has 3 quant files, from 7.5 GB (Q4_K_M) to 24.5 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M7.5 GB 9.3 GB
Too big Get file →
Q8_013.0 GB 14.9 GB
Too big Get file →
BF1624.5 GB 26.3 GB
Too big Get file →

What GPU do you need for mistral nemo gec?

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 Q4_K_M (7.5 GB file, about 9.3 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (13.0 GB file, about 14.9 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (13.0 GB file, about 14.9 GB in use).
  • 32 GB VRAM: the best quant that fits is BF16 (24.5 GB file, about 26.3 GB in use).

Which mistral nemo gec quant should you choose?

Q4_K_M is the usual starting point for mistral nemo gec: it balances file size and quality well. Here it is a 7.5 GB file.

The Q8_0 file is 13.0 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

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 byculverscruple
FamilyMistral
Licenseapache-2.0
Downloads (HF)11
Last updated2024-09-26

Frequently asked questions about mistral nemo gec

How much VRAM does mistral nemo gec need?

About 9.3 GB at Q4_K_M with an 8K context window. That is the 7.5 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 mistral nemo gec on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of mistral nemo gec GGUF?

It depends on the quant: Q4_K_M is 7.5 GB, Q8_0 is 13.0 GB, BF16 is 24.5 GB.

What context length does mistral nemo gec 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 mistral nemo gec GGUF?

The files are on Hugging Face in the culverscruple/mistral-nemo-gec repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does mistral nemo gec 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.

Similar models

Browse all →

More from culverscruple

All by culverscruple →

More Mistral models

All Mistral →

Other medium models

All medium models →