Starlight Synthesis 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 11 quants, from 11.9 GB (Q2_K) to 32.6 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 128.8 GB.
Starlight Synthesis 31B – 30.7B gemma4 model with vision and roleplay
Starlight Synthesis 31B is a 30.7B parameter gemma4 model. It supports vision and roleplay. The model is released under the apache-2.0 license.
Good at
- Vision tasks
- Roleplay dialogue
- Creative writing
Limits
- No vision support in some quantizations
- Large VRAM requirement for full context
- Requires apache-2.0 compliant usage
Best for
- Interactive fiction
- Long‑form storytelling
- Creative writing projects
Who it’s for. Developers and researchers needing a large vision‑capable model for roleplay or creative writing. The model is suitable for projects that can accommodate its memory footprint and license terms.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 11.9 GB | 44.6 GB | Too big | Get file → | |
| Q3_K_S | 13.8 GB | 46.5 GB | Too big | Get file → | |
| Q3_K_M | 15.3 GB | 48.0 GB | Too big | Get file → | |
| Q3_K_L | 16.6 GB | 49.3 GB | Too big | Get file → | |
| IQ4_XS | 16.9 GB | 49.6 GB | Too big | Get file → | |
| Q4_K_S | 17.8 GB | 50.5 GB | Too big | Get file → | |
| Q4_K_M | 18.7 GB | 51.4 GB | Too big | Get file → | |
| Q5_K_S | 21.3 GB | 54.0 GB | Too big | Get file → | |
| Q5_K_M | 21.8 GB | 54.6 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 Q2_K (11.92 GB file, 44.6 GB memory at 8k context). For 16 GB VRAM, Q4_K_M (18.69 GB file, 51.4 GB memory) is a good balance. For 32 GB VRAM, Q8_0 (32.64 GB file, 65.3 GB memory) provides the highest quality.
What GPU do you need for Starlight Synthesis 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 Q3_K_M (15.3 GB file, about 48.0 GB in use).
Which Starlight Synthesis 31B quant should you choose?
Q4_K_M is the usual starting point for Starlight Synthesis 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.
If memory is tight, the smallest file is Q2_K at 11.9 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Starlight Synthesis 31B
How much VRAM does Starlight Synthesis 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 Starlight Synthesis 31B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 44.6 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Starlight Synthesis 31B GGUF?
It depends on the quant: Q2_K is 11.9 GB, Q3_K_S is 13.8 GB, Q3_K_M is 15.3 GB, Q3_K_L is 16.6 GB, IQ4_XS is 16.9 GB, Q4_K_S is 17.8 GB and 5 more.
What context length does Starlight Synthesis 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 Starlight Synthesis 31B GGUF?
The files are on Hugging Face in the mradermacher/Starlight-Synthesis-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 Starlight Synthesis 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 Starlight Synthesis 31B on 8 GB VRAM?
Only the Q2_K quant (11.92 GB file) can be loaded with 8 GB VRAM, but it still requires about 44.6 GB memory at 8k context, so it is not feasible on 8 GB VRAM.
Does the model support vision?
Yes, the model has detected vision abilities and can process image inputs.
What license applies to this model?
The model is released under the apache-2.0 license.