MI

mistral-7b-reference-instruction2

MistralGGUF by pereUpdated 2024-05-20
Download on Hugging Face
Parameters7.24B
Context2K
Layers32
Architecturellama
Smallest quant4.4 GB
Quick answer

mistral-7b-reference-instruction2 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.

mistral-7b-reference-instruction2 is a 7.24B-parameter Mistral model in GGUF format, quantized by pere. Its trained context length is 2K tokens. The repository has 1 quant file, from 4.4 GB (Q4_K_M) to 4.4 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M4.4 GB 5.1 GB
Fits Get file →

What GPU do you need for mistral-7b-reference-instruction2?

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).

Which mistral-7b-reference-instruction2 quant should you choose?

Q4_K_M is the usual starting point for mistral-7b-reference-instruction2: 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
Parameters7.24B
Layers32
Trained context2,048 tokens
KV cache (fp16)128 KB per token

Source

Quantized bypere
FamilyMistral
Licensemit
Downloads (HF)17
Last updated2024-05-20

Frequently asked questions about mistral-7b-reference-instruction2

How much VRAM does mistral-7b-reference-instruction2 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 mistral-7b-reference-instruction2 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 mistral-7b-reference-instruction2 GGUF?

It depends on the quant: Q4_K_M is 4.4 GB.

What context length does mistral-7b-reference-instruction2 support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 1.1 GB at 8K and 0.3 GB at 2K.

Where can I download mistral-7b-reference-instruction2 GGUF?

The files are on Hugging Face in the pere/mistral-7b-reference-instruction2-Q4_K_M-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-7b-reference-instruction2 use?

Hugging Face lists the license as mit. 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 pere

All by pere →

More Mistral models

All Mistral →

Other small models

All small models →