Gemma-4-Dark-Orthia-31B needs about 52.6 GB of memory at Q4_K_M (a 19.8 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 8 quants, from 16.4 GB (Q3_K_M) to 64.2 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 128.8 GB.
Gemma-4-Dark-Orthia-31B is a 32.1B-parameter Gemma model in GGUF format, quantized by QuantaPlanta. Its trained context length is 256K tokens. The repository has 8 quant files, from 16.4 GB (Q3_K_M) to 64.2 GB (BF16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_M | 16.4 GB | 49.2 GB | Too big | Get file → | |
| Q4_K_S | 18.9 GB | 51.6 GB | Too big | Get file → | |
| Q4_K_M | 19.8 GB | 52.6 GB | Too big | Get file → | |
| Q5_K_S | 22.5 GB | 55.2 GB | Too big | Get file → | |
| Q5_K_M | 23.0 GB | 55.7 GB | Too big | Get file → | |
| Q6_K | 26.4 GB | 59.1 GB | Too big | Get file → | |
| Q8_0 | 34.1 GB | 66.8 GB | Too big | Get file → | |
| BF16 | 64.2 GB | 96.9 GB | Too big | Get file → |
What GPU do you need for Gemma-4-Dark-Orthia-31B?
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: no quant fits at an 8K context.
- 24 GB VRAM: no quant fits at an 8K context.
- 32 GB VRAM: no quant fits at an 8K context.
- 48 GB VRAM: no quant fits at an 8K context.
Which Gemma-4-Dark-Orthia-31B quant should you choose?
Q4_K_M is the usual starting point for Gemma-4-Dark-Orthia-31B: it balances file size and quality well. Here it is a 19.8 GB file.
The Q8_0 file is 34.1 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 Q3_K_M at 16.4 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
Frequently asked questions about Gemma-4-Dark-Orthia-31B
How much VRAM does Gemma-4-Dark-Orthia-31B need?
About 52.6 GB at Q4_K_M with an 8K context window. That is the 19.8 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-4-Dark-Orthia-31B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 49.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Gemma-4-Dark-Orthia-31B GGUF?
It depends on the quant: Q3_K_M is 16.4 GB, Q4_K_S is 18.9 GB, Q4_K_M is 19.8 GB, Q5_K_S is 22.5 GB, Q5_K_M is 23.0 GB, Q6_K is 26.4 GB and 2 more.
What context length does Gemma-4-Dark-Orthia-31B support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 32.2 GB at 8K and 128.8 GB at 32K.
Where can I download Gemma-4-Dark-Orthia-31B GGUF?
The files are on Hugging Face in the QuantaPlanta/Gemma-4-Dark-Orthia-31B-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-4-Dark-Orthia-31B use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.