MI

mistral-7b-v0.3-bnb-4bit

MistralGGUF by DiluzxUpdated 2024-07-08
Download on Hugging Face
Parameters7.25B
Context32K
Layers32
Architecturellama
Smallest quant5.1 GB
Quick answer

mistral-7b-v0.3-bnb-4bit needs about 6.7 GB of memory at Q5_K_M (a 5.1 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 2 quants, from 5.1 GB (Q5_K_M) to 14.5 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

mistral-7b-v0.3-bnb-4bit is a 7.25B-parameter Mistral model in GGUF format, quantized by Diluzx. Its trained context length is 32K tokens. The repository has 2 quant files, from 5.1 GB (Q5_K_M) to 14.5 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_M5.1 GB 6.7 GB
Fits Get file →
F1614.5 GB 16.1 GB
Too big Get file →

What GPU do you need for mistral-7b-v0.3-bnb-4bit?

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: the best quant that fits is Q5_K_M (5.1 GB file, about 6.7 GB in use).
  • 12 GB VRAM: the best quant that fits is Q5_K_M (5.1 GB file, about 6.7 GB in use).
  • 16 GB VRAM: the best quant that fits is Q5_K_M (5.1 GB file, about 6.7 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (14.5 GB file, about 16.1 GB in use).

Which mistral-7b-v0.3-bnb-4bit quant should you choose?

Q5_K_M (5.1 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters7.25B
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized byDiluzx
FamilyMistral
Licenseapache-2.0
Downloads (HF)30
Last updated2024-07-08

Frequently asked questions about mistral-7b-v0.3-bnb-4bit

How much VRAM does mistral-7b-v0.3-bnb-4bit need?

About 6.7 GB at Q5_K_M with an 8K context window. That is the 5.1 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 mistral-7b-v0.3-bnb-4bit on an 8 GB GPU?

Yes, with Q5_K_M: the 5.1 GB file needs about 6.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of mistral-7b-v0.3-bnb-4bit GGUF?

It depends on the quant: Q5_K_M is 5.1 GB, F16 is 14.5 GB.

What context length does mistral-7b-v0.3-bnb-4bit support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download mistral-7b-v0.3-bnb-4bit GGUF?

The files are on Hugging Face in the Diluzx/mistral-7b-v0.3-bnb-4bit 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-7b-v0.3-bnb-4bit 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-v0.3-bnb-4bit

Similar models

Browse all →

More from Diluzx

All by Diluzx →

More Mistral models

All Mistral →

Other small models

All small models →