MI

Midnight Rose 103B v1.0

MidnightGGUF by Artefact2Updated 2024-02-05
Download on Hugging Face
Parameters103B
Context4K
Layers120
Architecturellama
Smallest quant27.3 GB
Quick answer

Midnight Rose 103B v1.0 needs about 39.6 GB of memory at Q2_K_S (a 35.1 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 6 quants, from 27.3 GB (IQ2_XXS) to 49.6 GB (Q3_K_M).

Midnight Rose 103B v1.0 is a 103B-parameter Midnight model in GGUF format, quantized by Artefact2. Its trained context length is 4K tokens. The repository has 6 quant files, from 27.3 GB (IQ2_XXS) to 49.6 GB (Q3_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_XXS27.3 GB 29.8 GB
Too big Get file →
IQ2_XS30.4 GB 32.9 GB
Too big Get file →
Q2_K_S35.1 GB 37.6 GB
Too big Get file →
Q2_K37.9 GB 40.4 GB
Too big Get file →
IQ3_XXS40.2 GB 42.7 GB
Too big Get file →
Q3_K_M49.6 GB 52.1 GB
Too big Get file →

What GPU do you need for Midnight Rose 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: the best quant that fits is IQ2_XXS (27.3 GB file, about 31.8 GB in use).
  • 48 GB VRAM: the best quant that fits is IQ3_XXS (40.2 GB file, about 44.8 GB in use).

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

Q2_K_S (35.1 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.

If memory is tight, the smallest file is IQ2_XXS at 27.3 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 context4,096 tokens
KV cache (fp16)480 KB per token

Source

Quantized byArtefact2
FamilyMidnight
Licensellama2
Downloads (HF)113
Last updated2024-02-05

Frequently asked questions about Midnight Rose 103B v1.0

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

About 39.6 GB at Q2_K_S with an 8K context window. That is the 35.1 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 Midnight Rose 103B v1.0 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 31.8 GB, so you would need a larger GPU or CPU offloading.

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

It depends on the quant: IQ2_XXS is 27.3 GB, IQ2_XS is 30.4 GB, Q2_K_S is 35.1 GB, Q2_K is 37.9 GB, IQ3_XXS is 40.2 GB, Q3_K_M is 49.6 GB.

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

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 4.0 GB at 8K and 2.0 GB at 4K.

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

The files are on Hugging Face in the Artefact2/Midnight-Rose-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.

What license does Midnight Rose 103B v1.0 use?

Hugging Face lists the license as llama2. 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 Artefact2

All by Artefact2 →

More Midnight models

All Midnight →

Other large models

All large models →