EV

General Purpose 3B

EverythingGGUF by jeikuUpdated 2024-01-26
Download on Hugging Face
Parameters2.8B
Context4K
Layers32
Architecturestablelm
Smallest quant1.1 GB
Quick answer

General Purpose 3B needs about 4.9 GB of memory at Q4_K (a 1.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 7 quants, from 1.1 GB (Q2_K) to 5.6 GB (F16).

General Purpose 3B is a 2.8B-parameter Everything model in GGUF format, quantized by jeiku. Its trained context length is 4K tokens. The repository has 7 quant files, from 1.1 GB (Q2_K) to 5.6 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1.1 GB 2.9 GB
Fits Get file →
Q3_K1.4 GB 3.2 GB
Fits Get file →
Q4_K_S1.6 GB 3.5 GB
Fits Get file →
Q4_K1.7 GB 3.6 GB
Fits Get file →
Q5_K2.0 GB 3.8 GB
Fits Get file →
Q6_K2.3 GB 4.1 GB
Fits Get file →
F165.6 GB 7.4 GB
Tight Get file →

What GPU do you need for General Purpose 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: no quant fits at an 8K context.
  • 6 GB VRAM: the best quant that fits is Q6_K (2.3 GB file, about 5.5 GB in use).
  • 8 GB VRAM: the best quant that fits is Q6_K (2.3 GB file, about 5.5 GB in use).
  • 12 GB VRAM: the best quant that fits is F16 (5.6 GB file, about 8.8 GB in use).

Which General Purpose 3B quant should you choose?

Q4_K (1.7 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

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

Architecturestablelm
Parameters2.8B
Layers32
Trained context4,096 tokens
KV cache (fp16)320 KB per token

Source

Quantized byjeiku
Downloads (HF)5
Last updated2024-01-26

Frequently asked questions about General Purpose 3B

How much VRAM does General Purpose 3B need?

About 4.9 GB at Q4_K with an 8K context window. That is the 1.7 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 General Purpose 3B on an 8 GB GPU?

Yes, with Q6_K: the 2.3 GB file needs about 5.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of General Purpose 3B GGUF?

It depends on the quant: Q2_K is 1.1 GB, Q3_K is 1.4 GB, Q4_K_S is 1.6 GB, Q4_K is 1.7 GB, Q5_K is 2.0 GB, Q6_K is 2.3 GB and 1 more.

What context length does General Purpose 3B support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 2.7 GB at 8K and 1.3 GB at 4K.

Where can I download General Purpose 3B GGUF?

The files are on Hugging Face in the jeiku/General_Purpose_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 jeiku

All by jeiku →

More Everything models

All Everything →

Other tiny models

All tiny models →