Gemma 3 270m needs about 0.9 GB of memory at Q4_K_M (a 0.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 51 quants, from 0.2 GB (Q3_K_S) to 1.1 GB (F32). Longer context needs more: at 32K tokens the KV cache alone adds about 0.6 GB.
Gemma 3 270m – a compact 0.268B parameter model
Gemma 3 270m is a 0.268 billion parameter language model from Google, released under the gemma license. It supports a 32768 token context window and is available in multiple GGUF quantizations. The model is suited for lightweight inference on modest hardware.
Good at
- Fast inference on small GPUs
- Low memory footprint
- Supports long context
Limits
- No vision support
- No mixture of experts
- License restricts commercial use
Best for
- Embedded chatbots
- Local code generation
- Educational demos
Who it’s for. Developers needing a small, fast language model for local deployment. Researchers testing new quantization techniques may also find it useful.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_S | 0.2 GB | 0.9 GB | Fits | Get file → | |
| Q3_K_S | 0.2 GB | 0.9 GB | Fits | Get file → | |
| IQ1_M | 0.2 GB | 0.9 GB | Fits | Get file → | |
| IQ1_S | 0.2 GB | 0.9 GB | Fits | Get file → | |
| IQ2_S | 0.2 GB | 0.9 GB | Fits | Get file → | |
| IQ2_XS | 0.2 GB | 0.9 GB | Fits | Get file → | |
| IQ2_XXS | 0.2 GB | 0.9 GB | Fits | Get file → | |
| IQ3_S | 0.2 GB | 0.9 GB | Fits | Get file → | |
| Q2_K | 0.2 GB | 0.9 GB | Fits | Get file → | |
| Q2_K_S | 0.2 GB | 0.9 GB | Fits | Get file → | |
| IQ3_S | 0.2 GB | 0.9 GB | Fits | Get file → | |
| Q2_K | 0.2 GB | 0.9 GB | Fits | Get file → | |
| Q2_K_S | 0.2 GB | 0.9 GB | Fits | Get file → | |
| IQ3_XXS | 0.2 GB | 0.9 GB | Fits | Get file → | |
| IQ3_XXS | 0.2 GB | 0.9 GB | Fits | Get file → | |
| IQ4_XS | 0.2 GB | 0.9 GB | Fits | Get file → | |
| IQ4_XS | 0.2 GB | 0.9 GB | Fits | Get file → | |
| Q4_0 | 0.2 GB | 0.9 GB | Fits | Get file → | |
| Q4_0 | 0.2 GB | 0.9 GB | Fits | Get file → | |
| Q3_K_M | 0.2 GB | 0.9 GB | Fits | Get file → | |
| Q3_K_M | 0.2 GB | 0.9 GB | Fits | Get file → | |
| IQ4_NL | 0.2 GB | 0.9 GB | Fits | Get file → | |
| IQ4_NL | 0.2 GB | 0.9 GB | Fits | Get file → | |
| Q3_K_L | 0.2 GB | 0.9 GB | Fits | Get file → | |
| Q3_K_L | 0.2 GB | 0.9 GB | Fits | Get file → | |
| Q4_1 | 0.2 GB | 0.9 GB | Fits | Get file → | |
| Q4_1 | 0.2 GB | 0.9 GB | Fits | Get file → | |
| Q4_K_S | 0.2 GB | 0.9 GB | Fits | Get file → | |
| Q4_K_S | 0.2 GB | 0.9 GB | Fits | Get file → | |
| Q4_K_M | 0.3 GB | 0.9 GB | Fits | Get file → | |
| Q4_K_M | 0.3 GB | 0.9 GB | Fits | Get file → | |
| Q5_0 | 0.3 GB | 0.9 GB | Fits | Get file → | |
| Q5_0 | 0.3 GB | 0.9 GB | Fits | Get file → | |
| Q5_K_S | 0.3 GB | 0.9 GB | Fits | Get file → | |
| Q5_K_S | 0.3 GB | 0.9 GB | Fits | Get file → | |
| Q5_K_M | 0.3 GB | 0.9 GB | Fits | Get file → | |
| Q5_K_M | 0.3 GB | 0.9 GB | Fits | Get file → | |
| Q5_1 | 0.3 GB | 0.9 GB | Fits | Get file → | |
| Q5_1 | 0.3 GB | 0.9 GB | Fits | Get file → | |
| Q6_K | 0.3 GB | 0.9 GB | Fits | Get file → | |
| Q6_K | 0.3 GB | 0.9 GB | Fits | Get file → | |
| MXFP4_MOE | 0.3 GB | 0.9 GB | Fits | Get file → | |
| Q8_0 | 0.3 GB | 0.9 GB | Fits | Get file → | |
| MXFP4_MOE | 0.3 GB | 0.9 GB | Fits | Get file → | |
| Q8_0 | 0.3 GB | 0.9 GB | Fits | Get file → | |
| BF16 | 0.5 GB | 1.2 GB | Fits | Get file → | |
| F16 | 0.5 GB | 1.2 GB | Fits | Get file → | |
| BF16 | 0.5 GB | 1.2 GB | Fits | Get file → | |
| F16 | 0.5 GB | 1.2 GB | Fits | Get file → | |
| F32 | 1.1 GB | 1.7 GB | Fits | Get file → | |
| F32 | 1.1 GB | 1.7 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_0 or Q4_K_S (file size 0.25 GB, memory 0.9 GB). If you have 4 GB VRAM, choose Q3_K_S or IQ1_M (0.24 GB). For higher precision, Q8_0 (0.29 GB) or BF16 (0.54 GB) can be used on 12 GB VRAM systems.
What GPU do you need for Gemma 3 270m?
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 F32 (1.1 GB file, about 1.7 GB in use).
Which Gemma 3 270m quant should you choose?
Q4_K_M is the usual starting point for Gemma 3 270m: it balances file size and quality well. Here it is a 0.3 GB file.
The Q8_0 file is 0.3 GB, about 1.2 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 Q3_K_S at 0.2 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
Source
Frequently asked questions about Gemma 3 270m
How much VRAM does Gemma 3 270m need?
About 0.9 GB at Q4_K_M with an 8K context window. That is the 0.3 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 Gemma 3 270m on an 8 GB GPU?
Yes, with F32: the 1.1 GB file needs about 1.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Gemma 3 270m GGUF?
It depends on the quant: Q3_K_S is 0.2 GB, Q3_K_S is 0.2 GB, IQ1_M is 0.2 GB, IQ1_S is 0.2 GB, IQ2_S is 0.2 GB, IQ2_XS is 0.2 GB and 45 more.
What context length does Gemma 3 270m support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.6 GB at 32K.
Where can I download Gemma 3 270m GGUF?
The files are on Hugging Face in the gguf-org/gemma-3-270m-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 270m 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 270m on 8 GB VRAM?
Yes, a Q4_0 quantized file uses about 0.9 GB VRAM, leaving room for other processes.
Does this model support image input?
No, Gemma 3 270m is a text-only model with no vision capabilities.
What is the maximum context length?
The model supports up to 32768 tokens in context.