gemma 3 4b Tower crane needs about 9.4 GB of memory at F16 (a 7.8 GB file) with an 8K context window, so it fits on a 12 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.6 GB.
gemma 3 4b Tower crane is a 3.88B-parameter Gemma model in GGUF format, quantized by mky1324. Its trained context length is 128K tokens. The repository has 1 quant file, from 7.8 GB (F16) to 7.8 GB (F16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| F16 | 7.8 GB | 9.4 GB | Too big | Get file → |
What GPU do you need for gemma 3 4b Tower crane?
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 F16 (7.8 GB file, about 9.4 GB in use).
Which gemma 3 4b Tower crane quant should you choose?
F16 (7.8 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about gemma 3 4b Tower crane
How much VRAM does gemma 3 4b Tower crane need?
About 9.4 GB at F16 with an 8K context window. That is the 7.8 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 4b Tower crane on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 9.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of gemma 3 4b Tower crane GGUF?
It depends on the quant: F16 is 7.8 GB.
What context length does gemma 3 4b Tower crane support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.6 GB at 32K.
Where can I download gemma 3 4b Tower crane GGUF?
The files are on Hugging Face in the mky1324/gemma-3-4b-Tower_crane-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.