DA

datagemma rag 27b it

DatagemmaGGUF by bartowskiUpdated 2024-09-12
Download on Hugging Face
Parameters27.2B
Context8K
Layers46
Architecturegemma2
Smallest quant7.6 GB
Quick answer

datagemma rag 27b it 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 25 quants, from 7.6 GB (IQ2_XXS) to 54.5 GB (F16).

Datagemma RAG 27B IT – 27.2B parameter Gemma2 model

Datagemma RAG 27B IT is a 27.2B parameter Gemma2 model trained on 8192 context tokens. It is available in multiple GGUF quantizations from IQ2_XXS to Q8_0. The model is released under the gemma license and does not support system prompts.

Good at

  • Large context handling
  • High parameter count
  • Gemma2 architecture

Limits

  • No system prompt support
  • Requires 8k context for estimates
  • Large memory for higher quants

Best for

  • Research prototypes
  • Context‑heavy inference
  • Fine‑tuning on local hardware

Who it’s for. Developers and researchers needing a large Gemma2 model for local inference. The model is suitable for users with sufficient GPU or CPU memory to accommodate the chosen quantization.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_XXS7.6 GB 11.2 GB
Too big Get file →
IQ2_M9.4 GB 13.0 GB
Too big Get file →
Q2_K10.4 GB 14.0 GB
Too big Get file →
Q2_K_L10.7 GB 14.3 GB
Too big Get file →
IQ3_XS11.6 GB 15.1 GB
Too big Get file →
Q3_K_S12.2 GB 15.8 GB
Too big Get file →
IQ3_M12.5 GB 16.0 GB
Too big Get file →
Q3_K_M13.4 GB 17.0 GB
Too big Get file →
Q3_K_L14.5 GB 18.1 GB
Too big Get file →
Q3_K_XL14.8 GB 18.4 GB
Too big Get file →
IQ4_XS14.8 GB 18.4 GB
Too big Get file →
Q4_015.6 GB 19.2 GB
Too big Get file →
Q4_015.6 GB 19.2 GB
Too big Get file →
Q4_015.6 GB 19.2 GB
Too big Get file →
Q4_015.7 GB 19.3 GB
Too big Get file →
Q4_K_S15.7 GB 19.3 GB
Too big Get file →
Q4_K_M16.6 GB 20.2 GB
Too big Get file →
Q4_K_L16.9 GB 20.5 GB
Too big Get file →
Q5_K_S18.9 GB 22.5 GB
Too big Get file →
Q5_K_M19.4 GB 23.0 GB
Too big Get file →
Q5_K_L19.7 GB 23.3 GB
Too big Get file →
Q6_K22.3 GB 25.9 GB
Too big Get file →
Q6_K_L22.6 GB 26.2 GB
Too big Get file →
Q8_028.9 GB 32.5 GB
Too big Get file →
F1654.5 GB (2 parts) 58.0 GB
Too big Get file →

For 8 GB VRAM, use IQ2_XXS (file size 7.63 GB, estimated 11.2 GB memory). For 12 GB VRAM, IQ2_M (9.4 GB, 13 GB memory) or Q2_K (10.45 GB, 14 GB memory). For 16 GB VRAM, Q4_K_M (16.65 GB, 20.2 GB memory) or Q5_K_S (18.88 GB, 22.5 GB memory). Higher quants require more memory.

What GPU do you need for datagemma rag 27b it?

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: the best quant that fits is IQ2_XXS (7.6 GB file, about 11.2 GB in use).
  • 16 GB VRAM: the best quant that fits is IQ3_M (12.5 GB file, about 16.0 GB in use).
  • 24 GB VRAM: the best quant that fits is Q5_K_L (19.7 GB file, about 23.3 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K_L (22.6 GB file, about 26.2 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (28.9 GB file, about 32.5 GB in use).

Which datagemma rag 27b it quant should you choose?

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

The Q8_0 file is 28.9 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 IQ2_XXS at 7.6 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

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

Source

Quantized bybartowski
FamilyDatagemma
Licensegemma
Downloads (HF)1,334
Last updated2024-09-12

Frequently asked questions about datagemma rag 27b it

How much VRAM does datagemma rag 27b it 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 datagemma rag 27b it on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 11.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of datagemma rag 27b it GGUF?

It depends on the quant: IQ2_XXS is 7.6 GB, IQ2_M is 9.4 GB, Q2_K is 10.4 GB, Q2_K_L is 10.7 GB, IQ3_XS is 11.6 GB, Q3_K_S is 12.2 GB and 19 more.

What context length does datagemma rag 27b it 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 datagemma rag 27b it GGUF?

The files are on Hugging Face in the bartowski/datagemma-rag-27b-it-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 datagemma rag 27b it 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.

Can I run this model on 8 GB VRAM?

Use the IQ2_XXS quant, which has a file size of 7.63 GB and an estimated memory usage of 11.2 GB at 8k context.

Does this model support system prompts?

No, the model does not support a system prompt.

What is the context length of this model?

The model was trained with a context length of 8192 tokens.

Other GGUFs of datagemma-rag-27b-it

Similar models

Browse all →

More from bartowski

All by bartowski →

More Datagemma models

All Datagemma →

Other medium models

All medium models →