Gemma 4 31B needs about 51.4 GB of memory at Q4_K_M (a 18.7 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 3 quants, from 18.7 GB (Q4_K_M) to 32.6 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 128.8 GB.
Gemma 4 31B – 31 billion‑parameter multimodal instruction‑tuned model
Gemma 4 31B is a 31 billion‑parameter instruction‑tuned model that supports text and image input. It offers a 256 K‑token context window and multilingual support for over 140 languages. The model is released under the Apache 2.0 license.
Good at
- Multimodal text‑image generation
- Large‑context reasoning
- Instruction‑driven dialogue
Limits
- Requires 65 GB VRAM for Q8_0 at 8 K context
- No native vision support in quantized form
- License is Apache 2.0 – no commercial restrictions
Best for
- High‑capacity local inference
- Complex reasoning tasks
- Multimodal content creation
Who it’s for. Developers needing a powerful local LLM for reasoning and multimodal tasks. Suitable for servers with ample GPU memory and users who prefer open‑source models.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 18.7 GB | 51.4 GB | Too big | Get file → | |
| Q6_K | 25.2 GB | 57.9 GB | Too big | Get file → | |
| Q8_0 | 32.6 GB | 65.3 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (18.69 GB file, ~51 GB memory). For 16 GB VRAM, Q6_K (25.2 GB file, ~58 GB memory). For 32 GB VRAM or higher, Q8_0 (32.64 GB file, ~65 GB memory). Estimates are approximate.
What GPU do you need for Gemma 4 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 31B quant should you choose?
Q4_K_M is the usual starting point for Gemma 4 31B: it balances file size and quality well. Here it is a 18.7 GB file.
The Q8_0 file is 32.6 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Gemma 4 31B
How much VRAM does Gemma 4 31B need?
About 51.4 GB at Q4_K_M with an 8K context window. That is the 18.7 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 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 51.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Gemma 4 31B GGUF?
It depends on the quant: Q4_K_M is 18.7 GB, Q6_K is 25.2 GB, Q8_0 is 32.6 GB.
What context length does Gemma 4 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 31B GGUF?
The files are on Hugging Face in the lmstudio-community/gemma-4-31B-it-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 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.
Can I run Gemma 4 31B on 8 GB VRAM?
No, the smallest quant requires about 51 GB of VRAM at 8 K context. 8 GB VRAM is insufficient.
Does the model support image input?
Yes, Gemma 4 31B is multimodal and handles text and image input.
What license applies to this model?
The model is released under the Apache 2.0 license.