GE

Big Tiger Gemma 27B v3

GemmaGGUF by bartowskiUpdated 2025-07-09
Download on Hugging Face
Parameters28.4B
Context128K
Layers62
Architecturegemma3
Smallest quant8.1 GB
Quick answer

Big Tiger Gemma 27B v3 needs about 22.0 GB of memory at Q4_K_M (a 17.3 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 27 quants, from 8.1 GB (IQ2_XXS) to 56.8 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 16.6 GB.

Gemma 3 27B tuned for vision and neutral tone

Big Tiger Gemma 27B v3 is a 27B parameter Gemma3 model tuned for vision and a more neutral tone. It supports 131072 context tokens and is available in multiple GGUF quantizations.

Good at

  • Vision tasks
  • Neutral tone responses
  • Steerable hard‑topic handling

Limits

  • No explicit license listed
  • No chat template specified
  • Large memory requirement for high‑quality quants

Best for

  • Vision‑enabled chatbots
  • Content moderation tools
  • AI research prototypes

Who it’s for. Developers and researchers who need a vision‑capable Gemma model with a neutral tone. The model is suitable for applications that require large context windows and steerable responses.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_XXS8.1 GB 12.8 GB
Too big Get file →
IQ2_XS8.9 GB 13.6 GB
Too big Get file →
IQ2_S9.4 GB 14.0 GB
Too big Get file →
IQ2_M10.1 GB 14.8 GB
Too big Get file →
Q2_K11.0 GB 15.6 GB
Too big Get file →
IQ3_XXS11.3 GB 16.0 GB
Too big Get file →
IQ3_XS12.2 GB 16.8 GB
Too big Get file →
Q2_K_L12.3 GB 17.0 GB
Too big Get file →
Q3_K_S12.8 GB 17.4 GB
Too big Get file →
IQ3_M13.2 GB 17.8 GB
Too big Get file →
Q3_K_M14.0 GB 18.7 GB
Too big Get file →
Q3_K_L15.1 GB 19.8 GB
Too big Get file →
IQ4_XS15.5 GB 20.2 GB
Too big Get file →
IQ4_NL16.4 GB 21.0 GB
Too big Get file →
Q3_K_XL16.4 GB 21.0 GB
Too big Get file →
Q4_016.4 GB 21.1 GB
Too big Get file →
Q4_K_S16.5 GB 21.1 GB
Too big Get file →
Q4_K_M17.3 GB 22.0 GB
Too big Get file →
Q4_118.0 GB 22.7 GB
Too big Get file →
Q4_K_L18.4 GB 23.0 GB
Too big Get file →
Q5_K_S19.7 GB 24.4 GB
Too big Get file →
Q5_K_M20.2 GB 24.9 GB
Too big Get file →
Q5_K_L21.1 GB 25.8 GB
Too big Get file →
Q6_K23.3 GB 28.0 GB
Too big Get file →
Q6_K_L24.0 GB 28.7 GB
Too big Get file →
Q8_030.2 GB 34.9 GB
Too big Get file →
BF1656.8 GB (2 parts) 61.5 GB
Too big Get file →

For 8 GB VRAM, use IQ2_XXS (file size 8.15 GB, ~12.8 GB memory at 8 k context). For 16 GB VRAM, IQ4_0 (file size 16.41 GB, ~21.1 GB memory) or Q4_K_S (file size 16.47 GB, ~21.1 GB memory). For 32 GB VRAM, Q6_K (file size 23.32 GB, ~28 GB memory) or Q6_K_L (file size 24.01 GB, ~28.7 GB memory).

What GPU do you need for Big Tiger Gemma 27B v3?

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: the best quant that fits is IQ3_XXS (11.3 GB file, about 16.0 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_K_L (18.4 GB file, about 23.0 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K_L (24.0 GB file, about 28.7 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (30.2 GB file, about 34.9 GB in use).

Which Big Tiger Gemma 27B v3 quant should you choose?

Q4_K_M is the usual starting point for Big Tiger Gemma 27B v3: it balances file size and quality well. Here it is a 17.3 GB file.

The Q8_0 file is 30.2 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 8.1 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

Architecturegemma3
Parameters28.4B
Layers62
Trained context131,072 tokens
KV cache (fp16)496 KB per token

Source

Quantized bybartowski
FamilyGemma
Downloads (HF)3,148
Last updated2025-07-09

Frequently asked questions about Big Tiger Gemma 27B v3

How much VRAM does Big Tiger Gemma 27B v3 need?

About 22.0 GB at Q4_K_M with an 8K context window. That is the 17.3 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 Big Tiger Gemma 27B v3 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 12.8 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Big Tiger Gemma 27B v3 GGUF?

It depends on the quant: IQ2_XXS is 8.1 GB, IQ2_XS is 8.9 GB, IQ2_S is 9.4 GB, IQ2_M is 10.1 GB, Q2_K is 11.0 GB, IQ3_XXS is 11.3 GB and 21 more.

What context length does Big Tiger Gemma 27B v3 support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 4.2 GB at 8K and 16.6 GB at 32K.

Where can I download Big Tiger Gemma 27B v3 GGUF?

The files are on Hugging Face in the bartowski/TheDrummer_Big-Tiger-Gemma-27B-v3-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run Big Tiger Gemma 27B v3 on 8 GB VRAM?

Use the IQ2_XXS quant, which requires about 12.8 GB of memory at 8 k context. It will fit on 8 GB VRAM with some swapping.

Does the model support vision?

Yes, the model is vision capable as indicated in the detected abilities.

What is the context length of this model?

The model supports 131072 context tokens.

Other GGUFs of Big-Tiger-Gemma-27B-v3

Similar models

Browse all →

More from bartowski

All by bartowski →

More Gemma models

All Gemma →

Other medium models

All medium models →