Gemma 4 31B it ROCmFP4 needs about 31.2 GB of memory at Q6_0 (a 28.6 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 5 quants, from 0.5 GB (Q8_0) to 32.3 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.
Gemma 4 31B it ROCmFP4 is a 30.7B-parameter Gemma model in GGUF format, quantized by kingjones777. Its trained context length is 256K tokens. The repository has 5 quant files, from 0.5 GB (Q8_0) to 32.3 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 0.5 GB | 3.2 GB | Fits | Get file → | |
| Q4_0 | 17.7 GB | 20.3 GB | Too big | Get file → | |
| Q6_0 | 28.6 GB | 31.2 GB | Too big | Get file → | |
| Q8_0 | 31.7 GB | 34.4 GB | Too big | Get file → | |
| Q8_0 | 32.3 GB | 34.9 GB | Too big | Get file → |
What GPU do you need for Gemma 4 31B it ROCmFP4?
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 Q8_0 (0.5 GB file, about 3.2 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (0.5 GB file, about 3.2 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (0.5 GB file, about 3.2 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (0.5 GB file, about 3.2 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (0.5 GB file, about 3.2 GB in use).
- 24 GB VRAM: the best quant that fits is Q4_0 (17.7 GB file, about 20.3 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_0 (28.6 GB file, about 31.2 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (32.3 GB file, about 34.9 GB in use).
Which Gemma 4 31B it ROCmFP4 quant should you choose?
Q6_0 (28.6 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.
If memory is tight, the smallest file is Q8_0 at 0.5 GB, with the quality trade-offs that come with fewer bits. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Gemma 4 31B it ROCmFP4
How much VRAM does Gemma 4 31B it ROCmFP4 need?
About 31.2 GB at Q6_0 with an 8K context window. That is the 28.6 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 31B it ROCmFP4 on an 8 GB GPU?
Yes, with Q8_0: the 0.5 GB file needs about 3.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Gemma 4 31B it ROCmFP4 GGUF?
It depends on the quant: Q8_0 is 0.5 GB, Q4_0 is 17.7 GB, Q6_0 is 28.6 GB, Q8_0 is 31.7 GB, Q8_0 is 32.3 GB.
What context length does Gemma 4 31B it ROCmFP4 support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.
Where can I download Gemma 4 31B it ROCmFP4 GGUF?
The files are on Hugging Face in the kingjones777/Gemma-4-31B-it-ROCmFP4-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 31B it ROCmFP4 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.