MI

mistral new

MistralGGUF by SibinrajUpdated 2024-08-05
Download on Hugging Face
Parameters7.24B
Context32K
Layers—
Architecturellama
Smallest quant0.2 GB
Quick answer

mistral new needs about 0.7 GB of memory at Q4_K_M (a 0.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 0.2 GB (Q4_K_M) to 14.5 GB (F16).

mistral new is a 7.24B-parameter Mistral model in GGUF format, quantized by Sibinraj. Its trained context length is 32K tokens. The repository has 4 quant files, from 0.2 GB (Q4_K_M) to 14.5 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M0.2 GB 0.7 GB
Fits Get file →
Q5_K_M0.3 GB 0.8 GB
Fits Get file →
Q8_00.4 GB 0.9 GB
Fits Get file →
F1614.5 GB 16.7 GB
Too big Get file →

What GPU do you need for mistral new?

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: the best quant that fits is Q8_0 (0.4 GB file, about 0.9 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (0.4 GB file, about 0.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (0.4 GB file, about 0.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (0.4 GB file, about 0.9 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (0.4 GB file, about 0.9 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (14.5 GB file, about 16.7 GB in use).

Which mistral new quant should you choose?

Q4_K_M is the usual starting point for mistral new: it balances file size and quality well. Here it is a 0.2 GB file.

The Q8_0 file is 0.4 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters7.24B
Trained context32,768 tokens

Source

Quantized bySibinraj
FamilyMistral
Licenseapache-2.0
Downloads (HF)62
Last updated2024-08-05

Frequently asked questions about mistral new

How much VRAM does mistral new need?

About 0.7 GB at Q4_K_M with an 8K context window. That is the 0.2 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 mistral new on an 8 GB GPU?

Yes, with Q8_0: the 0.4 GB file needs about 0.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of mistral new GGUF?

It depends on the quant: Q4_K_M is 0.2 GB, Q5_K_M is 0.3 GB, Q8_0 is 0.4 GB, F16 is 14.5 GB.

What context length does mistral new support?

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

Where can I download mistral new GGUF?

The files are on Hugging Face in the Sibinraj/mistral_new-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 mistral new use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Other GGUFs of mistral-7b-instruct-v0.2-bnb-4bit

Similar models

Browse all →

More from Sibinraj

All by Sibinraj →

More Mistral models

All Mistral →

Other small models

All small models →