MI

japanese mistral 300m base

MistralGGUF by ce-leryUpdated 2023-12-21
Download on Hugging Face
Parameters355M
Context4K
Layers24
Architecturellama
Smallest quant1.4 GB
Quick answer

japanese mistral 300m base needs about 2.3 GB of memory at F32 (a 1.4 GB file) with an 8K context window, so it fits on a 4 GB GPU.

japanese mistral 300m base is a 355M-parameter Mistral model in GGUF format, quantized by ce-lery. Its trained context length is 4K tokens. The repository has 1 quant file, from 1.4 GB (F32) to 1.4 GB (F32).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F321.4 GB 2.1 GB
Fits Get file →

What GPU do you need for japanese mistral 300m base?

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: the best quant that fits is F32 (1.4 GB file, about 2.3 GB in use).

Which japanese mistral 300m base quant should you choose?

F32 (1.4 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters355M
Layers24
Trained context4,096 tokens
KV cache (fp16)48 KB per token

Source

Quantized byce-lery
FamilyMistral
Downloads (HF)377
Last updated2023-12-21

Frequently asked questions about japanese mistral 300m base

How much VRAM does japanese mistral 300m base need?

About 2.3 GB at F32 with an 8K context window. That is the 1.4 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 japanese mistral 300m base on an 8 GB GPU?

Yes, with F32: the 1.4 GB file needs about 2.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of japanese mistral 300m base GGUF?

It depends on the quant: F32 is 1.4 GB.

What context length does japanese mistral 300m base support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 0.4 GB at 8K and 0.2 GB at 4K.

Where can I download japanese mistral 300m base GGUF?

The files are on Hugging Face in the ce-lery/japanese-mistral-300m-base 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 tiny models

All tiny models →