MI

Mistral_7B_CrewAI

MistralGGUF by flock-ioUpdated 2024-04-29
Download on Hugging Face
Parameters7.24B
Context32K
Layers32
Architecturellama
Smallest quant4.4 GB
Quick answer

Mistral_7B_CrewAI needs about 9.3 GB of memory at F16 (a 7.7 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 3 quants, from 4.4 GB (F16) to 14.5 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Mistral_7B_CrewAI is a 7.24B-parameter Mistral model in GGUF format, quantized by flock-io. Its trained context length is 32K tokens. The repository has 3 quant files, from 4.4 GB (F16) to 14.5 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F164.4 GB 5.9 GB
Fits Get file →
F167.7 GB 9.3 GB
Too big Get file →
F1614.5 GB 16.1 GB
Too big Get file →

What GPU do you need for Mistral_7B_CrewAI?

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 F16 (4.4 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is F16 (4.4 GB file, about 5.9 GB in use).
  • 12 GB VRAM: the best quant that fits is F16 (7.7 GB file, about 9.3 GB in use).
  • 16 GB VRAM: the best quant that fits is F16 (7.7 GB file, about 9.3 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_CrewAI quant should you choose?

F16 (7.7 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

If memory is tight, the smallest file is F16 at 4.4 GB, with the quality trade-offs that come with fewer bits. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

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 byflock-io
FamilyMistral
Downloads (HF)22
Last updated2024-04-29

Frequently asked questions about Mistral_7B_CrewAI

How much VRAM does Mistral_7B_CrewAI need?

About 9.3 GB at F16 with an 8K context window. That is the 7.7 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_CrewAI on an 8 GB GPU?

Yes, with F16: 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_CrewAI GGUF?

It depends on the quant: F16 is 4.4 GB, F16 is 7.7 GB, F16 is 14.5 GB.

What context length does Mistral_7B_CrewAI 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_CrewAI GGUF?

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

Similar models

Browse all →

More Mistral models

All Mistral →

Other small models

All small models →