gemma-4-31B needs about 65.3 GB of memory at Q8_0 (a 32.6 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 2 quants, from 32.6 GB (Q8_0) to 61.4 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 128.8 GB.
Gemma 4 31B multimodal model with 256K token context
Gemma 4 31B is a multimodal LLM that handles text and image input and generates text output. It supports a context window of 262144 tokens and is released under the Apache 2.0 license. The model is available in two GGUF quantizations.
Good at
- Large context handling
- Multimodal text and image processing
- Instruction‑tuned generation
Limits
- Requires large VRAM (≈65.3 GB for Q8_0 at 8 k context)
- No audio support in this size
- License requires attribution
Best for
- Long‑form content creation
- Multimodal chatbots
- Research prototyping
Who it’s for. Developers and researchers needing a high‑capacity multimodal model for local deployment. The model is suitable for servers or workstations with ample GPU memory.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 32.6 GB | 65.3 GB | Too big | Get file → | |
| BF16 | 61.4 GB | 94.1 GB | Too big | Get file → |
For 8 GB VRAM use Q8_0 (32.64 GB file, ~65.3 GB memory at 8 k context). For larger budgets use BF16 (61.41 GB file, ~94.1 GB memory at 8 k context). 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?
Q8_0 (32.6 GB) is the middle option in this repository. 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
How much VRAM does gemma-4-31B need?
About 65.3 GB at Q8_0 with an 8K context window. That is the 32.6 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 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 65.3 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: Q8_0 is 32.6 GB, BF16 is 61.4 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 ggml-org/gemma-4-31B-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-4-31B 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 ~65.3 GB VRAM at 8 k context. You need a GPU with much larger memory.
Does this model support audio?
Audio is not supported in the 31B variant; only text and image inputs are available.
What license applies?
The model is released under the Apache 2.0 license, which allows free use with attribution.