MI

MiniChat 2 3B q4f16

MinichatGGUF by lrsoftUpdated 2024-05-09
Download on Hugging Face
Parameters3.02B
Context4K
Layers24
Architecturellama
Smallest quant1.9 GB
Quick answer

MiniChat 2 3B q4f16 needs about 4.8 GB of memory at its main file (a 1.9 GB file) with an 8K context window, so it fits on a 6 GB GPU.

MiniChat 2 3B q4f16 is a 3.02B-parameter Minichat model in GGUF format, quantized by lrsoft. Its trained context length is 4K tokens. The repository has 1 quant file, from 1.9 GB to 1.9 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—1.9 GB 3.6 GB
Fits Get file →

What GPU do you need for MiniChat 2 3B q4f16?

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 the main file (1.9 GB file, about 4.8 GB in use).

Specifications

Architecture from the GGUF header

Architecturellama
Parameters3.02B
Layers24
Trained context4,096 tokens
KV cache (fp16)288 KB per token

Source

Quantized bylrsoft
FamilyMinichat
Licenseapache-2.0
Downloads (HF)13
Last updated2024-05-09

Frequently asked questions about MiniChat 2 3B q4f16

How much VRAM does MiniChat 2 3B q4f16 need?

About 4.8 GB at its main file with an 8K context window. That is the 1.9 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 MiniChat 2 3B q4f16 on an 8 GB GPU?

Yes, with the smaller files: the 1.9 GB file needs about 4.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of MiniChat 2 3B q4f16 GGUF?

It depends on the quant: file is 1.9 GB.

What context length does MiniChat 2 3B q4f16 support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 2.4 GB at 8K and 1.2 GB at 4K.

Where can I download MiniChat 2 3B q4f16 GGUF?

The files are on Hugging Face in the lrsoft/MiniChat-2-3B-q4f16-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 MiniChat 2 3B q4f16 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.

Similar models

Browse all →

More from lrsoft

All by lrsoft →

More Minichat models

All Minichat →

Other tiny models

All tiny models →