MI

retroturn

MistralGGUF by defenUpdated 2024-12-14
Download on Hugging Face
Parameters22.2B
Context32K
Layers—
Architecturellama
Smallest quant18.3 GB
Quick answer

retroturn needs about 20.9 GB of memory at its main file (a 18.3 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 2 quants, from 18.3 GB to 44.5 GB (F16).

retroturn is a 22.2B-parameter Mistral model in GGUF format, quantized by defen. Its trained context length is 32K tokens. The repository has 2 quant files, from 18.3 GB to 44.5 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—18.3 GB 20.9 GB
Too big Get file →
F1644.5 GB 50.3 GB
Too big Get file →

What GPU do you need for retroturn?

These figures add the file size, an fp16 KV cache at an 8K context window 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: the best quant that fits is the main file (18.3 GB file, about 20.9 GB in use).
  • 32 GB VRAM: the best quant that fits is the main file (18.3 GB file, about 20.9 GB in use).
  • 48 GB VRAM: the best quant that fits is the main file (18.3 GB file, about 20.9 GB in use).

Specifications

Architecture from the GGUF header

Architecturellama
Parameters22.2B
Trained context32,768 tokens

Source

Quantized bydefen
FamilyMistral
Repositorydefen/retroturn
Downloads (HF)0
Last updated2024-12-14

Frequently asked questions about retroturn

How much VRAM does retroturn need?

About 20.9 GB at its main file with an 8K context window. That is the 18.3 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 retroturn on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 20.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of retroturn GGUF?

It depends on the quant: file is 18.3 GB, F16 is 44.5 GB.

What context length does retroturn support?

The GGUF header lists a trained context length of 32,768 tokens (32K).

Where can I download retroturn GGUF?

The files are on Hugging Face in the defen/retroturn repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Other GGUFs of Mistral-Small-Instruct-2409

Similar models

Browse all →

More from defen

All by defen →

More Mistral models

All Mistral →

Other medium models

All medium models →