CO

MTSAIR Cotype Nano MLX

CotypeGGUF by mlx-communityUpdated 2024-11-29
Download on Hugging Face
Parameters1.54B
Context32K
Layers28
Architectureqwen2
Smallest quant3.1 GB
Quick answer

MTSAIR Cotype Nano MLX needs about 3.8 GB of memory at F16 (a 3.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 0.9 GB.

MTSAIR Cotype Nano MLX is a 1.54B-parameter Cotype model in GGUF format, quantized by mlx-community. Its trained context length is 32K tokens. The repository has 1 quant file, from 3.1 GB (F16) to 3.1 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F163.1 GB 3.8 GB
Fits Get file →

What GPU do you need for MTSAIR Cotype Nano MLX?

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 F16 (3.1 GB file, about 3.8 GB in use).

Which MTSAIR Cotype Nano MLX quant should you choose?

F16 (3.1 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

Architectureqwen2
Parameters1.54B
Layers28
Trained context32,768 tokens
KV cache (fp16)28 KB per token

Source

Quantized bymlx-community
FamilyCotype
Licenseapache-2.0
Downloads (HF)22
Last updated2024-11-29

Frequently asked questions about MTSAIR Cotype Nano MLX

How much VRAM does MTSAIR Cotype Nano MLX need?

About 3.8 GB at F16 with an 8K context window. That is the 3.1 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 MTSAIR Cotype Nano MLX on an 8 GB GPU?

Yes, with F16: the 3.1 GB file needs about 3.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of MTSAIR Cotype Nano MLX GGUF?

It depends on the quant: F16 is 3.1 GB.

What context length does MTSAIR Cotype Nano MLX support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.9 GB at 32K.

Where can I download MTSAIR Cotype Nano MLX GGUF?

The files are on Hugging Face in the mlx-community/MTSAIR-Cotype-Nano-MLX-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 MTSAIR Cotype Nano MLX 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 Cotype-Nano

Similar models

Browse all →

More from mlx-community

All by mlx-community →

More Cotype models

All Cotype →

Other tiny models

All tiny models →