MI

Midnight Miqu 103B v1.0

MidnightGGUF by DraconesUpdated 2024-03-07
Download on Hugging Face
Parameters103B
Context32K
Layers120
Architecturellama
Smallest quant37.9 GB
Quick answer

Midnight Miqu 103B v1.0 needs about 46.6 GB of memory at IQ3_XXS (a 42.0 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 5 quants, from 37.9 GB (Q2_K) to 49.6 GB (Q3_K_M).

Midnight Miqu 103B v1.0 is a 103B-parameter Midnight model in GGUF format, quantized by Dracones. Its trained context length is 32K tokens. The repository has 5 quant files, from 37.9 GB (Q2_K) to 49.6 GB (Q3_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K37.9 GB 42.4 GB
Too big Get file →
Q3_K_XS42.0 GB 46.5 GB
Too big Get file →
IQ3_XXS42.0 GB 46.6 GB
Too big Get file →
Q3_K_S44.5 GB 49.0 GB
Too big Get file →
Q3_K_M49.6 GB 54.1 GB
Too big Get file →

What GPU do you need for Midnight Miqu 103B v1.0?

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: the best quant that fits is IQ3_XXS (42.0 GB file, about 46.6 GB in use).

Which Midnight Miqu 103B v1.0 quant should you choose?

IQ3_XXS (42.0 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.

If memory is tight, the smallest file is Q2_K at 37.9 GB, with the quality trade-offs that come with fewer bits. 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
Parameters103B
Layers120
Trained context32,764 tokens
KV cache (fp16)480 KB per token

Source

Quantized byDracones
FamilyMidnight
Downloads (HF)243
Last updated2024-03-07

Frequently asked questions about Midnight Miqu 103B v1.0

How much VRAM does Midnight Miqu 103B v1.0 need?

About 46.6 GB at IQ3_XXS with an 8K context window. That is the 42.0 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 Midnight Miqu 103B v1.0 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 42.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Midnight Miqu 103B v1.0 GGUF?

It depends on the quant: Q2_K is 37.9 GB, Q3_K_XS is 42.0 GB, IQ3_XXS is 42.0 GB, Q3_K_S is 44.5 GB, Q3_K_M is 49.6 GB.

What context length does Midnight Miqu 103B v1.0 support?

The GGUF header lists a trained context length of 32,764 tokens (32K). The KV cache grows with the context you use: about 4.0 GB at 8K and 16.1 GB at 32K.

Where can I download Midnight Miqu 103B v1.0 GGUF?

The files are on Hugging Face in the Dracones/Midnight-Miqu-103B-v1.0-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 Dracones

All by Dracones →

More Midnight models

All Midnight →

Other large models

All large models →