MI

model3.0_

MistralGGUF by RohithqwertyUpdated 2024-07-08
Download on Hugging Face
Parameters7.25B
Context32K
Layers32
Architecturellama
Smallest quant4.4 GB
Quick answer

model3.0_ needs about 5.9 GB of memory at Q4_K_M (a 4.4 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 2 quants, from 4.4 GB (Q4_K_M) to 14.5 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

model3.0_ is a 7.25B-parameter Mistral model in GGUF format, quantized by Rohithqwerty. Its trained context length is 32K tokens. The repository has 2 quant files, from 4.4 GB (Q4_K_M) to 14.5 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M4.4 GB 5.9 GB
Fits Get file →
F1614.5 GB 16.1 GB
Too big Get file →

What GPU do you need for model3.0_?

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: the best quant that fits is Q4_K_M (4.4 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q4_K_M (4.4 GB file, about 5.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q4_K_M (4.4 GB file, about 5.9 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_K_M (4.4 GB file, about 5.9 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (14.5 GB file, about 16.1 GB in use).

Which model3.0_ quant should you choose?

Q4_K_M is the usual starting point for model3.0_: it balances file size and quality well. Here it is a 4.4 GB file.

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 byRohithqwerty
FamilyMistral
Licenseapache-2.0
Downloads (HF)26
Last updated2024-07-08

Frequently asked questions about model3.0_

How much VRAM does model3.0_ need?

About 5.9 GB at Q4_K_M with an 8K context window. That is the 4.4 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 model3.0_ on an 8 GB GPU?

Yes, with Q4_K_M: the 4.4 GB file needs about 5.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of model3.0_ GGUF?

It depends on the quant: Q4_K_M is 4.4 GB, F16 is 14.5 GB.

What context length does model3.0_ 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 model3.0_ GGUF?

The files are on Hugging Face in the Rohithqwerty/model3.0_ repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does model3.0_ 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 Rohithqwerty

All by Rohithqwerty →

More Mistral models

All Mistral →

Other small models

All small models →