GE

vntl gemma2 27b

GemmaGGUF by lmg-anonUpdated 2024-07-08
Download on Hugging Face
Parameters27.2B
Context8K
Layers46
Architecturegemma2
Smallest quant13.4 GB
Quick answer

vntl gemma2 27b needs about 20.2 GB of memory at Q4_K_M (a 16.6 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 5 quants, from 13.4 GB (Q3_K_M) to 54.5 GB (BF16).

vntl gemma2 27b is a 27.2B-parameter Gemma model in GGUF format, quantized by lmg-anon. Its trained context length is 8K tokens. The repository has 5 quant files, from 13.4 GB (Q3_K_M) to 54.5 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_M13.4 GB 17.0 GB
Too big Get file →
Q4_K_M16.6 GB 20.2 GB
Too big Get file →
Q5_K_M19.4 GB 23.0 GB
Too big Get file →
Q6_K22.3 GB 25.9 GB
Too big Get file →
BF1654.5 GB (2 parts) 58.0 GB
Too big Get file →

What GPU do you need for vntl gemma2 27b?

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: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: the best quant that fits is Q5_K_M (19.4 GB file, about 23.0 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (22.3 GB file, about 25.9 GB in use).
  • 48 GB VRAM: the best quant that fits is Q6_K (22.3 GB file, about 25.9 GB in use).

Which vntl gemma2 27b quant should you choose?

Q4_K_M is the usual starting point for vntl gemma2 27b: it balances file size and quality well. Here it is a 16.6 GB file.

If memory is tight, the smallest file is Q3_K_M at 13.4 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

Architecturegemma2
Parameters27.2B
Layers46
Trained context8,192 tokens
KV cache (fp16)368 KB per token

Source

Quantized bylmg-anon
FamilyGemma
Licensegemma
Downloads (HF)342
Last updated2024-07-08

Frequently asked questions about vntl gemma2 27b

How much VRAM does vntl gemma2 27b need?

About 20.2 GB at Q4_K_M with an 8K context window. That is the 16.6 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 vntl gemma2 27b on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 17.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of vntl gemma2 27b GGUF?

It depends on the quant: Q3_K_M is 13.4 GB, Q4_K_M is 16.6 GB, Q5_K_M is 19.4 GB, Q6_K is 22.3 GB, BF16 is 54.5 GB.

What context length does vntl gemma2 27b support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 3.1 GB at 8K and 3.1 GB at 8K.

Where can I download vntl gemma2 27b GGUF?

The files are on Hugging Face in the lmg-anon/vntl-gemma2-27b-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 vntl gemma2 27b use?

Hugging Face lists the license as gemma. 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 lmg-anon

All by lmg-anon →

More Gemma models

All Gemma →

Other medium models

All medium models →