DA

NinjaMouse2 2.5B v0.1

DanubeGGUF by trollekUpdated 2024-05-07
Download on Hugging Face
Parameters2.53B
Context8K
Layers34
Architecturellama
Smallest quant1.5 GB
Quick answer

NinjaMouse2 2.5B v0.1 needs about 2.7 GB of memory at Q4_K_M (a 1.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 1.5 GB (Q4_K_M) to 2.1 GB (Q6_K).

NinjaMouse2 2.5B v0.1 is a 2.53B-parameter Danube model in GGUF format, quantized by trollek. Its trained context length is 8K tokens. The repository has 2 quant files, from 1.5 GB (Q4_K_M) to 2.1 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M1.5 GB 2.7 GB
Fits Get file →
Q6_K2.1 GB 3.3 GB
Fits Get file →

What GPU do you need for NinjaMouse2 2.5B v0.1?

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 Q6_K (2.1 GB file, about 3.3 GB in use).

Which NinjaMouse2 2.5B v0.1 quant should you choose?

Q4_K_M is the usual starting point for NinjaMouse2 2.5B v0.1: it balances file size and quality well. Here it is a 1.5 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters2.53B
Layers34
Trained context8,192 tokens
KV cache (fp16)85 KB per token

Source

Quantized bytrollek
FamilyDanube
Licenseapache-2.0
Downloads (HF)68
Last updated2024-05-07

Frequently asked questions about NinjaMouse2 2.5B v0.1

How much VRAM does NinjaMouse2 2.5B v0.1 need?

About 2.7 GB at Q4_K_M with an 8K context window. That is the 1.5 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 NinjaMouse2 2.5B v0.1 on an 8 GB GPU?

Yes, with Q6_K: the 2.1 GB file needs about 3.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of NinjaMouse2 2.5B v0.1 GGUF?

It depends on the quant: Q4_K_M is 1.5 GB, Q6_K is 2.1 GB.

What context length does NinjaMouse2 2.5B v0.1 support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 0.7 GB at 8K and 0.7 GB at 8K.

Where can I download NinjaMouse2 2.5B v0.1 GGUF?

The files are on Hugging Face in the trollek/NinjaMouse2-2.5B-v0.1-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 NinjaMouse2 2.5B v0.1 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 h2o-danube2-1.8b-chat

Similar models

Browse all →

More from trollek

All by trollek →

More Danube models

All Danube →

Other tiny models

All tiny models →