LU

SmartMaid 123

LumimaidGGUF by gghfezUpdated 2024-10-06
Download on Hugging Face
Parameters123B
Context128K
Layers88
Architecturellama
Smallest quant45.2 GB
Quick answer

SmartMaid 123 needs about 48.6 GB of memory at Q2_K_M (a 45.2 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 2 quants, from 45.2 GB (Q2_K_M) to 73.2 GB (Q4_K). Longer context needs more: at 32K tokens the KV cache alone adds about 11.8 GB.

SmartMaid 123 is a 123B-parameter Lumimaid model in GGUF format, quantized by gghfez. Its trained context length is 128K tokens. The repository has 2 quant files, from 45.2 GB (Q2_K_M) to 73.2 GB (Q4_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K_M45.2 GB 48.6 GB
Too big Get file →
Q4_K73.2 GB (2 parts) 76.7 GB
Too big Get file →

What GPU do you need for SmartMaid 123?

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: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 32 GB VRAM: no quant fits at an 8K context.
  • 48 GB VRAM: no quant fits at an 8K context.

Which SmartMaid 123 quant should you choose?

Q2_K_M (45.2 GB) is the middle option in this repository. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters123B
Layers88
Trained context131,072 tokens
KV cache (fp16)352 KB per token

Source

Quantized bygghfez
FamilyLumimaid
Licenseother
Downloads (HF)86
Last updated2024-10-06

Frequently asked questions about SmartMaid 123

How much VRAM does SmartMaid 123 need?

About 48.6 GB at Q2_K_M with an 8K context window. That is the 45.2 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 SmartMaid 123 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 48.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of SmartMaid 123 GGUF?

It depends on the quant: Q2_K_M is 45.2 GB, Q4_K is 73.2 GB.

What context length does SmartMaid 123 support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 3.0 GB at 8K and 11.8 GB at 32K.

Where can I download SmartMaid 123 GGUF?

The files are on Hugging Face in the gghfez/SmartMaid-123b-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does SmartMaid 123 use?

Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Other GGUFs of Lumimaid-v0.2-123B

Similar models

Browse all →

More from gghfez

All by gghfez →

More Lumimaid models

All Lumimaid →

Other large models

All large models →