MI

malawi mistral7b V1 8bt

MistralGGUF by JuliusFxUpdated 2024-03-02
Download on Hugging Face
Parameters7.24B
Context32K
Layers32
Architecturellama
Smallest quant5.2 GB
Quick answer

malawi mistral7b V1 8bt needs about 6.7 GB of memory at Q8_0 (a 5.2 GB file) with an 8K context window, so it fits on a 8 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

malawi mistral7b V1 8bt is a 7.24B-parameter Mistral model in GGUF format, quantized by JuliusFx. Its trained context length is 32K tokens. The repository has 1 quant file, from 5.2 GB (Q8_0) to 5.2 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_05.2 GB 6.7 GB
Fits Get file →

What GPU do you need for malawi mistral7b V1 8bt?

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: no quant fits at an 8K context.
  • 8 GB VRAM: the best quant that fits is Q8_0 (5.2 GB file, about 6.7 GB in use).

Which malawi mistral7b V1 8bt quant should you choose?

Q8_0 (5.2 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

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 byJuliusFx
FamilyMistral
Licenseapache-2.0
Downloads (HF)7
Last updated2024-03-02

Frequently asked questions about malawi mistral7b V1 8bt

How much VRAM does malawi mistral7b V1 8bt need?

About 6.7 GB at Q8_0 with an 8K context window. That is the 5.2 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 malawi mistral7b V1 8bt on an 8 GB GPU?

Yes, with Q8_0: the 5.2 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 malawi mistral7b V1 8bt GGUF?

It depends on the quant: Q8_0 is 5.2 GB.

What context length does malawi mistral7b V1 8bt 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 malawi mistral7b V1 8bt GGUF?

The files are on Hugging Face in the JuliusFx/malawi-mistral7b_V1-8bt repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does malawi mistral7b V1 8bt 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-bnb-4bit

Similar models

Browse all →

More Mistral models

All Mistral →

Other small models

All small models →