MI

Medilora Mistral 7B

MistralGGUF by MediloraUpdated 2023-12-06
Download on Hugging Face
Parameters7.24B
Context32K
Layers32
Architecturellama
Smallest quant3.8 GB
Quick answer

Medilora Mistral 7B needs about 5.7 GB of memory at Q4_K_S (a 4.1 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 3 quants, from 3.8 GB (Q3_K_L) to 14.5 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Medilora Mistral 7B is a 7.24B-parameter Mistral model in GGUF format, quantized by Medilora. Its trained context length is 32K tokens. The repository has 3 quant files, from 3.8 GB (Q3_K_L) to 14.5 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_L3.8 GB 5.4 GB
Fits Get file →
Q4_K_S4.1 GB 5.7 GB
Fits Get file →
F1614.5 GB 16.1 GB
Too big Get file →

What GPU do you need for Medilora Mistral 7B?

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_S (4.1 GB file, about 5.7 GB in use).
  • 8 GB VRAM: the best quant that fits is Q4_K_S (4.1 GB file, about 5.7 GB in use).
  • 12 GB VRAM: the best quant that fits is Q4_K_S (4.1 GB file, about 5.7 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_K_S (4.1 GB file, about 5.7 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (14.5 GB file, about 16.1 GB in use).

Which Medilora Mistral 7B quant should you choose?

Q4_K_S (4.1 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

If memory is tight, the smallest file is Q3_K_L at 3.8 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 byMedilora
FamilyMistral
Licensemit
Downloads (HF)220
Last updated2023-12-06

Frequently asked questions about Medilora Mistral 7B

How much VRAM does Medilora Mistral 7B need?

About 5.7 GB at Q4_K_S with an 8K context window. That is the 4.1 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 Medilora Mistral 7B on an 8 GB GPU?

Yes, with Q4_K_S: the 4.1 GB file needs about 5.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Medilora Mistral 7B GGUF?

It depends on the quant: Q3_K_L is 3.8 GB, Q4_K_S is 4.1 GB, F16 is 14.5 GB.

What context length does Medilora Mistral 7B 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 Medilora Mistral 7B GGUF?

The files are on Hugging Face in the Medilora/Medilora-Mistral-7B repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Medilora Mistral 7B 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 Mistral models

All Mistral →

Other small models

All small models →