TI

TinyExperts-v0-4x1B

TinyexpertsGGUF by RichardErkhovUpdated 2024-06-29
Download on Hugging Face
Parameters2.62B
Context32K
Layers22
Architecturellama
Smallest quant1.0 GB
Quick answer

TinyExperts-v0-4x1B needs about 1.7 GB of memory at Q2_K (a 1.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 1.0 GB (Q2_K) to 1.1 GB (IQ3_XS). Longer context needs more: at 32K tokens the KV cache alone adds about 0.7 GB.

TinyExperts-v0-4x1B is a 2.62B-parameter Tinyexperts model in GGUF format, quantized by RichardErkhov. Its trained context length is 32K tokens. The repository has 2 quant files, from 1.0 GB (Q2_K) to 1.1 GB (IQ3_XS).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1.0 GB 1.7 GB
Fits Get file →
IQ3_XS1.1 GB 1.8 GB
Fits Get file →

What GPU do you need for TinyExperts-v0-4x1B?

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 IQ3_XS (1.1 GB file, about 1.8 GB in use).

Which TinyExperts-v0-4x1B quant should you choose?

Q2_K (1.0 GB) is the middle option in this repository. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters2.62B (approximate, mixture of experts)
Layers22
Trained context32,768 tokens
KV cache (fp16)22 KB per token

Source

Quantized byRichardErkhov
Downloads (HF)4
Last updated2024-06-29

Frequently asked questions about TinyExperts-v0-4x1B

How much VRAM does TinyExperts-v0-4x1B need?

About 1.7 GB at Q2_K with an 8K context window. That is the 1.0 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 TinyExperts-v0-4x1B on an 8 GB GPU?

Yes, with IQ3_XS: the 1.1 GB file needs about 1.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of TinyExperts-v0-4x1B GGUF?

It depends on the quant: Q2_K is 1.0 GB, IQ3_XS is 1.1 GB.

What context length does TinyExperts-v0-4x1B 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 0.7 GB at 32K.

Where can I download TinyExperts-v0-4x1B GGUF?

The files are on Hugging Face in the RichardErkhov/beberik_-_TinyExperts-v0-4x1B-gguf 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 from RichardErkhov

All by RichardErkhov →

Other tiny models

All tiny models →