LU

Lumimaid v0.2 12B GGUF Imat

LumimaidGGUF by NerhessUpdated 2024-07-27
Download on Hugging Face
Parameters12.2B
Context1000K
Layers40
Architecturellama
Smallest quant6.7 GB
Quick answer

Lumimaid v0.2 12B GGUF Imat needs about 11.0 GB of memory at Q5_K_L (a 9.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 5 quants, from 6.7 GB (Q3_K_L) to 13.0 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

Lumimaid v0.2 12B GGUF Imat is a 12.2B-parameter Lumimaid model in GGUF format, quantized by Nerhess. Its trained context length is 1000K tokens. The repository has 5 quant files, from 6.7 GB (Q3_K_L) to 13.0 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_L6.7 GB 8.5 GB
Too big Get file →
Q4_K_L8.0 GB 9.8 GB
Too big Get file →
Q5_K_L9.1 GB 11.0 GB
Too big Get file →
Q6_K_L10.4 GB 12.2 GB
Too big Get file →
Q8_013.0 GB 14.9 GB
Too big Get file →

What GPU do you need for Lumimaid v0.2 12B GGUF Imat?

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 Q5_K_L (9.1 GB file, about 11.0 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (13.0 GB file, about 14.9 GB in use).

Which Lumimaid v0.2 12B GGUF Imat quant should you choose?

Q5_K_L (9.1 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

If memory is tight, the smallest file is Q3_K_L at 6.7 GB, with the quality trade-offs that come with fewer bits. 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 byNerhess
FamilyLumimaid
Downloads (HF)9
Last updated2024-07-27

Frequently asked questions about Lumimaid v0.2 12B GGUF Imat

How much VRAM does Lumimaid v0.2 12B GGUF Imat need?

About 11.0 GB at Q5_K_L with an 8K context window. That is the 9.1 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 Lumimaid v0.2 12B GGUF Imat on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 8.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Lumimaid v0.2 12B GGUF Imat GGUF?

It depends on the quant: Q3_K_L is 6.7 GB, Q4_K_L is 8.0 GB, Q5_K_L is 9.1 GB, Q6_K_L is 10.4 GB, Q8_0 is 13.0 GB.

What context length does Lumimaid v0.2 12B GGUF Imat 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 Lumimaid v0.2 12B GGUF Imat GGUF?

The files are on Hugging Face in the Nerhess/Lumimaid-v0.2-12B-GGUF-Imat repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Lumimaid v0.2 12B GGUF Imat use?

Hugging Face lists the license as cc-by-nc-4.0. 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 Lumimaid models

All Lumimaid →

Other medium models

All medium models →