LA

T0 3B

LarenspearGGUF by larenspearUpdated 2024-07-08
Download on Hugging Face
Parameters2.85B
Context512
Layers24
Architecturet5
Smallest quant1.1 GB
Quick answer

T0 3B needs about 3.9 GB of memory at Q4_K_M (a 1.8 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 10 quants, from 1.1 GB (Q2_K) to 3.0 GB (Q8_0).

T0 3B is a 2.85B-parameter Larenspear model in GGUF format, quantized by larenspear. Its trained context length is 512 tokens. The repository has 10 quant files, from 1.1 GB (Q2_K) to 3.0 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1.1 GB 1.7 GB
Fits Get file →
Q3_K_S1.3 GB 1.9 GB
Fits Get file →
Q3_K_M1.4 GB 2.0 GB
Fits Get file →
Q3_K_L1.5 GB 2.1 GB
Fits Get file →
Q4_K_S1.6 GB 2.2 GB
Fits Get file →
Q4_K_M1.8 GB 2.4 GB
Fits Get file →
Q5_K_S2.0 GB 2.6 GB
Fits Get file →
Q5_K_M2.0 GB 2.6 GB
Fits Get file →
Q6_K2.3 GB 2.9 GB
Fits Get file →
Q8_03.0 GB 3.6 GB
Fits Get file →

What GPU do you need for T0 3B?

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 Q4_K_M (1.8 GB file, about 3.9 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (3.0 GB file, about 5.1 GB in use).

Which T0 3B quant should you choose?

Q4_K_M is the usual starting point for T0 3B: it balances file size and quality well. Here it is a 1.8 GB file.

The Q8_0 file is 3.0 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q2_K at 1.1 GB, with the quality trade-offs that come with fewer bits. 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

Architecturet5
Parameters2.85B
Layers24
Trained context512 tokens
KV cache (fp16)192 KB per token

Source

Quantized bylarenspear
Downloads (HF)3
Last updated2024-07-08

Frequently asked questions about T0 3B

How much VRAM does T0 3B need?

About 3.9 GB at Q4_K_M with an 8K context window. That is the 1.8 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 T0 3B on an 8 GB GPU?

Yes, with Q8_0: the 3.0 GB file needs about 5.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of T0 3B GGUF?

It depends on the quant: Q2_K is 1.1 GB, Q3_K_S is 1.3 GB, Q3_K_M is 1.4 GB, Q3_K_L is 1.5 GB, Q4_K_S is 1.6 GB, Q4_K_M is 1.8 GB and 4 more.

What context length does T0 3B support?

The GGUF header lists a trained context length of 512 tokens (512). The KV cache grows with the context you use: about 1.6 GB at 8K and 0.1 GB at 512.

Where can I download T0 3B GGUF?

The files are on Hugging Face in the larenspear/T0_3B-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 larenspear

All by larenspear →

Other tiny models

All tiny models →