Gemma-3-27B-It-Qat needs about 21.2 GB of memory at Q4_K_M (a 16.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 25 quants, from 6.5 GB (IQ1_S) to 54.0 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 16.6 GB.
Gemma‑3‑27B‑It‑Qat – 27B multimodal instruction‑tuned model in GGUF format
Gemma‑3‑27B‑It‑Qat is a 27‑billion‑parameter multimodal model that accepts text and images. It is instruction‑tuned and supports a 128K context window. The model is available in multiple GGUF quantizations for different memory budgets.
Good at
- Multimodal text and image understanding
- Large context handling
- Instruction‑driven generation
Limits
- No vision support in some quantizations
- Large VRAM required for higher‑quality quants
- License is gemma – check terms
Best for
- Chatbots needing image input
- Document summarization with visual context
- Multilingual QA with large context
Who it’s for. Developers building multimodal applications on laptops or small servers. Researchers needing a 27B model with open weights and a 128K context window.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 6.5 GB | 11.2 GB | Too big | Get file → | |
| IQ1_M | 7.0 GB | 11.6 GB | Too big | Get file → | |
| IQ2_XXS | 7.9 GB | 12.5 GB | Too big | Get file → | |
| IQ2_M | 9.6 GB | 14.3 GB | Too big | Get file → | |
| Q2_K | 10.5 GB | 15.2 GB | Too big | Get file → | |
| Q2_K_L | 10.5 GB | 15.2 GB | Too big | Get file → | |
| Q2_K_XL | 10.7 GB | 15.3 GB | Too big | Get file → | |
| IQ3_XXS | 10.8 GB | 15.5 GB | Too big | Get file → | |
| Q3_K_S | 12.2 GB | 16.8 GB | Too big | Get file → | |
| Q3_K_M | 13.4 GB | 18.1 GB | Too big | Get file → | |
| Q3_K_XL | 13.7 GB | 18.4 GB | Too big | Get file → | |
| IQ4_XS | 14.8 GB | 19.4 GB | Too big | Get file → | |
| IQ4_NL | 15.6 GB | 20.2 GB | Too big | Get file → | |
| Q4_0 | 15.6 GB | 20.3 GB | Too big | Get file → | |
| Q4_K_S | 15.7 GB | 20.3 GB | Too big | Get file → | |
| Q4_K_M | 16.5 GB | 21.2 GB | Too big | Get file → | |
| Q4_K_XL | 16.8 GB | 21.5 GB | Too big | Get file → | |
| Q4_1 | 17.2 GB | 21.8 GB | Too big | Get file → | |
| Q5_K_S | 18.8 GB | 23.4 GB | Too big | Get file → | |
| Q5_K_M | 19.3 GB | 23.9 GB | Too big | Get file → | |
| Q5_K_XL | 19.3 GB | 24.0 GB | Too big | Get file → | |
| Q6_K | 22.2 GB | 26.8 GB | Too big | Get file → | |
| Q6_K_XL | 23.7 GB | 28.4 GB | Too big | Get file → | |
| Q8_K_XL | 31.8 GB | 36.5 GB | Too big | Get file → | |
| BF16 | 54.0 GB (2 parts) | 58.7 GB | Too big | Get file → |
For 8‑GB VRAM use IQ1_S (6.51 GB, ~11.2 GB RAM). For 12‑GB VRAM use IQ2_XXS (7.85 GB, ~12.5 GB RAM). For 16‑GB VRAM use Q4_0 (15.62 GB, ~20.3 GB RAM). Higher quants give better quality but need more memory.
What GPU do you need for Gemma-3-27B-It-Qat?
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 IQ1_M (7.0 GB file, about 11.6 GB in use).
- 16 GB VRAM: the best quant that fits is IQ3_XXS (10.8 GB file, about 15.5 GB in use).
- 24 GB VRAM: the best quant that fits is Q5_K_XL (19.3 GB file, about 24.0 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K_XL (23.7 GB file, about 28.4 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_K_XL (31.8 GB file, about 36.5 GB in use).
Which Gemma-3-27B-It-Qat quant should you choose?
Q4_K_M is the usual starting point for Gemma-3-27B-It-Qat: it balances file size and quality well. Here it is a 16.5 GB file.
If memory is tight, the smallest file is IQ1_S at 6.5 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
Source
Frequently asked questions about Gemma-3-27B-It-Qat
How much VRAM does Gemma-3-27B-It-Qat need?
About 21.2 GB at Q4_K_M with an 8K context window. That is the 16.5 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-3-27B-It-Qat 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 Gemma-3-27B-It-Qat GGUF?
It depends on the quant: IQ1_S is 6.5 GB, IQ1_M is 7.0 GB, IQ2_XXS is 7.9 GB, IQ2_M is 9.6 GB, Q2_K is 10.5 GB, Q2_K_L is 10.5 GB and 19 more.
What context length does Gemma-3-27B-It-Qat 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 Gemma-3-27B-It-Qat GGUF?
The files are on Hugging Face in the unsloth/gemma-3-27b-it-qat-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 Gemma-3-27B-It-Qat 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 Gemma‑3‑27B‑It‑Qat on 8 GB VRAM?
Yes, with the IQ1_S quant you need about 11.2 GB RAM, which fits on 8 GB VRAM with swap.
Does this model support image input?
Yes, it accepts images normalized to 896×896 and encoded to 256 tokens.
What is the context window size?
The model supports a 128K token context window.