GE

gemma ko 2b instruct v0.51

GemmaGGUF by lemon-mintUpdated 2024-04-02
Download on Hugging Face
Parameters2.51B
Context8K
Layers18
Architecturegemma
Smallest quant1.4 GB
Quick answer

gemma ko 2b instruct v0.51 needs about 2.3 GB of memory at Q4_K_M (a 1.6 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 5 quants, from 1.4 GB (Q3_K_M) to 5.0 GB.

gemma ko 2b instruct v0.51 is a 2.51B-parameter Gemma model in GGUF format, quantized by lemon-mint. Its trained context length is 8K tokens. The repository has 5 quant files, from 1.4 GB (Q3_K_M) to 5.0 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_M1.4 GB 2.0 GB
Fits Get file →
Q4_K_M1.6 GB 2.3 GB
Fits Get file →
Q5_K_M1.8 GB 2.5 GB
Fits Get file →
Q6_K2.1 GB 2.7 GB
Fits Get file →
—5.0 GB 5.7 GB
Fits Get file →

What GPU do you need for gemma ko 2b instruct v0.51?

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 2.7 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (5.0 GB file, about 5.7 GB in use).

Which gemma ko 2b instruct v0.51 quant should you choose?

Q4_K_M is the usual starting point for gemma ko 2b instruct v0.51: it balances file size and quality well. Here it is a 1.6 GB file.

If memory is tight, the smallest file is Q3_K_M at 1.4 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegemma
Parameters2.51B
Layers18
Trained context8,192 tokens
KV cache (fp16)18 KB per token

Source

Quantized bylemon-mint
FamilyGemma
Downloads (HF)106
Last updated2024-04-02

Frequently asked questions about gemma ko 2b instruct v0.51

How much VRAM does gemma ko 2b instruct v0.51 need?

About 2.3 GB at Q4_K_M with an 8K context window. That is the 1.6 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 gemma ko 2b instruct v0.51 on an 8 GB GPU?

Yes, with the smaller files: the 5.0 GB file needs about 5.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of gemma ko 2b instruct v0.51 GGUF?

It depends on the quant: Q3_K_M is 1.4 GB, Q4_K_M is 1.6 GB, Q5_K_M is 1.8 GB, Q6_K is 2.1 GB, file is 5.0 GB.

What context length does gemma ko 2b instruct v0.51 support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.2 GB at 8K.

Where can I download gemma ko 2b instruct v0.51 GGUF?

The files are on Hugging Face in the lemon-mint/gemma-ko-2b-instruct-v0.51-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 lemon-mint

All by lemon-mint →

More Gemma models

All Gemma →

Other tiny models

All tiny models →