MI

mistral ft optimized 1227

MistralGGUF by MirsadUpdated 2023-12-30
Download on Hugging Face
Parameters7.24B
Context32K
Layers32
Architecturellama
Smallest quant3.5 GB
Quick answer

mistral ft optimized 1227 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 3 quants, from 3.5 GB (Q3_K_M) to 5.1 GB (Q5_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

mistral ft optimized 1227 is a 7.24B-parameter Mistral model in GGUF format, quantized by Mirsad. Its trained context length is 32K tokens. The repository has 3 quant files, from 3.5 GB (Q3_K_M) to 5.1 GB (Q5_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_M3.5 GB 5.1 GB
Fits Get file →
Q4_K_M4.4 GB 5.9 GB
Fits Get file →
Q5_K_M5.1 GB 6.7 GB
Fits Get file →

What GPU do you need for mistral ft optimized 1227?

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 Q5_K_M (5.1 GB file, about 6.7 GB in use).

Which mistral ft optimized 1227 quant should you choose?

Q4_K_M is the usual starting point for mistral ft optimized 1227: it balances file size and quality well. Here it is a 4.4 GB file.

If memory is tight, the smallest file is Q3_K_M at 3.5 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters7.24B
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized byMirsad
FamilyMistral
Licenseapache-2.0
Downloads (HF)8
Last updated2023-12-30

Frequently asked questions about mistral ft optimized 1227

How much VRAM does mistral ft optimized 1227 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 ft optimized 1227 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 ft optimized 1227 GGUF?

It depends on the quant: Q3_K_M is 3.5 GB, Q4_K_M is 4.4 GB, Q5_K_M is 5.1 GB.

What context length does mistral ft optimized 1227 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 ft optimized 1227 GGUF?

The files are on Hugging Face in the Mirsad/mistral-ft-optimized-1227.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 ft optimized 1227 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.

Similar models

Browse all →

More from Mirsad

All by Mirsad →

More Mistral models

All Mistral →

Other small models

All small models →