SO

sophosympatheia Midnight Miqu 70B v1.5

SophosympatheiaGGUF by teneriffaUpdated 2024-03-30
Download on Hugging Face
Parameters69B
Context32K
Layers80
Architecturellama
Smallest quant39.2 GB
Quick answer

sophosympatheia Midnight Miqu 70B v1.5 needs about 42.4 GB of memory at IQ4_NL (a 39.2 GB file) with an 8K context window, so it fits on a 48 GB GPU.

sophosympatheia Midnight Miqu 70B v1.5 is a 69B-parameter Sophosympatheia model in GGUF format, quantized by teneriffa. Its trained context length is 32K tokens. The repository has 1 quant file, from 39.2 GB (IQ4_NL) to 39.2 GB (IQ4_NL).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ4_NL39.2 GB 42.4 GB
Too big Get file →

What GPU do you need for sophosympatheia Midnight Miqu 70B v1.5?

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 IQ4_NL (39.2 GB file, about 42.4 GB in use).

Which sophosympatheia Midnight Miqu 70B v1.5 quant should you choose?

IQ4_NL (39.2 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

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 byteneriffa
Downloads (HF)9
Last updated2024-03-30

Frequently asked questions about sophosympatheia Midnight Miqu 70B v1.5

How much VRAM does sophosympatheia Midnight Miqu 70B v1.5 need?

About 42.4 GB at IQ4_NL with an 8K context window. That is the 39.2 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 sophosympatheia Midnight Miqu 70B v1.5 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 sophosympatheia Midnight Miqu 70B v1.5 GGUF?

It depends on the quant: IQ4_NL is 39.2 GB.

What context length does sophosympatheia Midnight Miqu 70B v1.5 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 sophosympatheia Midnight Miqu 70B v1.5 GGUF?

The files are on Hugging Face in the teneriffa/sophosympatheia_Midnight-Miqu-70B-v1.5-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 sophosympatheia Midnight Miqu 70B v1.5 use?

Hugging Face lists the license as cc-by-sa-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 from teneriffa

All by teneriffa →

Other large models

All large models →