MI

romulus mistral nemo 12b simpo Q3 K L

MistralGGUF by Stark2008Updated 2024-07-30
Download on Hugging Face
Parameters12.2B
Context1000K
Layers40
Architecturellama
Smallest quant6.6 GB
Quick answer

romulus mistral nemo 12b simpo Q3 K L needs about 8.4 GB of memory at Q3_K_L (a 6.6 GB file) with an 8K context window, so it fits on a 12 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

romulus mistral nemo 12b simpo Q3 K L is a 12.2B-parameter Mistral model in GGUF format, quantized by Stark2008. Its trained context length is 1000K tokens. The repository has 1 quant file, from 6.6 GB (Q3_K_L) to 6.6 GB (Q3_K_L).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_L6.6 GB 8.4 GB
Too big Get file →

What GPU do you need for romulus mistral nemo 12b simpo Q3 K L?

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 Q3_K_L (6.6 GB file, about 8.4 GB in use).

Which romulus mistral nemo 12b simpo Q3 K L quant should you choose?

Q3_K_L (6.6 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

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 byStark2008
FamilyMistral
Downloads (HF)10
Last updated2024-07-30

Frequently asked questions about romulus mistral nemo 12b simpo Q3 K L

How much VRAM does romulus mistral nemo 12b simpo Q3 K L need?

About 8.4 GB at Q3_K_L with an 8K context window. That is the 6.6 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 romulus mistral nemo 12b simpo Q3 K L on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 8.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of romulus mistral nemo 12b simpo Q3 K L GGUF?

It depends on the quant: Q3_K_L is 6.6 GB.

What context length does romulus mistral nemo 12b simpo Q3 K L 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 romulus mistral nemo 12b simpo Q3 K L GGUF?

The files are on Hugging Face in the Stark2008/romulus-mistral-nemo-12b-simpo-Q3_K_L-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Other GGUFs of romulus-mistral-nemo-12b-simpo

Similar models

Browse all →

More from Stark2008

All by Stark2008 →

More Mistral models

All Mistral →

Other medium models

All medium models →