Split Untied 31B needs about 52.2 GB of memory at Q4_K_M (a 19.5 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 24 quants, from 0.0 GB to 26.4 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 128.8 GB.
Split Untied 31B – a large gemma4 model for roleplay
Split Untied 31B is a 31‑billion parameter gemma4 model. It is trained on 262,144 context tokens and licensed under Apache‑2.0. The model is available in multiple GGUF quantizations, ranging from 0.01 GB to 26.36 GB.
Good at
- Roleplay
- Large context handling
- High‑parameter density
Limits
- No vision support in provided files
- Requires 32 GB+ VRAM for full precision
- License is Apache‑2.0
Best for
- Chatbot development
- Creative writing prompts
- Long‑form dialogue generation
Who it’s for. Developers and researchers who need a large‑parameter gemma4 model for text‑only applications. The model is suitable for local deployment with sufficient GPU memory.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 32.7 GB | Too big | Get file → | |
| IQ1_S | 7.6 GB | 40.3 GB | Too big | Get file → | |
| IQ1_M | 8.2 GB | 40.9 GB | Too big | Get file → | |
| IQ2_XXS | 9.1 GB | 41.8 GB | Too big | Get file → | |
| IQ2_XS | 10.0 GB | 42.7 GB | Too big | Get file → | |
| IQ2_S | 10.8 GB | 43.5 GB | Too big | Get file → | |
| Q2_K_S | 11.4 GB | 44.2 GB | Too big | Get file → | |
| IQ2_M | 11.5 GB | 44.2 GB | Too big | Get file → | |
| Q2_K | 12.4 GB | 45.1 GB | Too big | Get file → | |
| IQ3_XXS | 12.7 GB | 45.4 GB | Too big | Get file → | |
| IQ3_XS | 13.7 GB | 46.4 GB | Too big | Get file → | |
| IQ3_S | 14.4 GB | 47.1 GB | Too big | Get file → | |
| Q3_K_S | 14.4 GB | 47.1 GB | Too big | Get file → | |
| IQ3_M | 15.0 GB | 47.7 GB | Too big | Get file → | |
| Q3_K_M | 15.9 GB | 48.6 GB | Too big | Get file → | |
| Q3_K_L | 17.2 GB | 49.9 GB | Too big | Get file → | |
| IQ4_XS | 17.5 GB | 50.2 GB | Too big | Get file → | |
| Q4_0 | 18.5 GB | 51.2 GB | Too big | Get file → | |
| Q4_K_S | 18.6 GB | 51.3 GB | Too big | Get file → | |
| Q4_K_M | 19.5 GB | 52.2 GB | Too big | Get file → | |
| Q4_1 | 20.4 GB | 53.1 GB | Too big | Get file → | |
| Q5_K_S | 22.3 GB | 55.0 GB | Too big | Get file → | |
| Q5_K_M | 22.8 GB | 55.5 GB | Too big | Get file → | |
| Q6_K | 26.4 GB | 59.1 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_S (18.56 GB file, ~51.3 GB VRAM at 8k context). For 12 GB VRAM, Q5_K_S (22.28 GB file, ~55 GB VRAM). For 16 GB VRAM, Q6_K (26.36 GB file, ~59.1 GB VRAM). Estimates are approximate.
What GPU do you need for Split Untied 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: the best quant that fits is IQ3_M (15.0 GB file, about 47.7 GB in use).
Which Split Untied 31B quant should you choose?
Q4_K_M is the usual starting point for Split Untied 31B: it balances file size and quality well. Here it is a 19.5 GB file.
If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Split Untied 31B
How much VRAM does Split Untied 31B need?
About 52.2 GB at Q4_K_M with an 8K context window. That is the 19.5 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 Split Untied 31B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 32.7 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Split Untied 31B GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 7.6 GB, IQ1_M is 8.2 GB, IQ2_XXS is 9.1 GB, IQ2_XS is 10.0 GB, IQ2_S is 10.8 GB and 18 more.
What context length does Split Untied 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 Split Untied 31B GGUF?
The files are on Hugging Face in the mradermacher/Split-Untied-31B-i1-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 Split Untied 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 Split Untied 31B on 8 GB VRAM?
Only the smallest quant (unknown) is 0.01 GB, but it still requires ~32.7 GB VRAM at 8k context. 8 GB VRAM is insufficient for any quant.
Does this model support vision?
No vision support is provided in the GGUF files listed.
What license applies to this model?
The model is licensed under Apache‑2.0.