MI

midnight miqu 70b v1.0

MidnightGGUF by oooozUpdated 2024-03-02
Download on Hugging Face
Parameters69B
Context32K
Layers80
Architecturellama
Smallest quant29.9 GB
Quick answer

midnight miqu 70b v1.0 needs about 44.6 GB of memory at Q4_K_M (a 41.4 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 6 quants, from 29.9 GB (Q3_K_S) to 48.8 GB (Q5_K_M).

midnight miqu 70b v1.0 is a 69B-parameter Midnight model in GGUF format, quantized by ooooz. Its trained context length is 32K tokens. The repository has 6 quant files, from 29.9 GB (Q3_K_S) to 48.8 GB (Q5_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_S29.9 GB 33.1 GB
Too big Get file →
Q3_K_M33.3 GB 36.5 GB
Too big Get file →
Q4_K_S39.2 GB 42.4 GB
Too big Get file →
Q4_K_M41.4 GB 44.6 GB
Too big Get file →
Q5_K_S47.5 GB 50.6 GB
Too big Get file →
Q5_K_M48.8 GB 51.9 GB
Too big Get file →

What GPU do you need for midnight miqu 70b 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 Q4_K_M (41.4 GB file, about 44.6 GB in use).

Which midnight miqu 70b v1.0 quant should you choose?

Q4_K_M is the usual starting point for midnight miqu 70b v1.0: it balances file size and quality well. Here it is a 41.4 GB file.

If memory is tight, the smallest file is Q3_K_S at 29.9 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
Parameters69B
Layers80
Trained context32,764 tokens
KV cache (fp16)320 KB per token

Source

Quantized byooooz
FamilyMidnight
Downloads (HF)115
Last updated2024-03-02

Frequently asked questions about midnight miqu 70b v1.0

How much VRAM does midnight miqu 70b v1.0 need?

About 44.6 GB at Q4_K_M with an 8K context window. That is the 41.4 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 70b v1.0 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 33.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of midnight miqu 70b v1.0 GGUF?

It depends on the quant: Q3_K_S is 29.9 GB, Q3_K_M is 33.3 GB, Q4_K_S is 39.2 GB, Q4_K_M is 41.4 GB, Q5_K_S is 47.5 GB, Q5_K_M is 48.8 GB.

What context length does midnight miqu 70b 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 2.7 GB at 8K and 10.7 GB at 32K.

Where can I download midnight miqu 70b v1.0 GGUF?

The files are on Hugging Face in the ooooz/midnight-miqu-70b-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 ooooz

All by ooooz →

More Midnight models

All Midnight →

Other large models

All large models →