Gemma 3 Starshine 12B needs about 11.0 GB of memory at Q4_K_M (a 7.3 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 24 quants, from 2.9 GB (IQ1_S) to 9.7 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 12.9 GB.
Gemma 3 Starshine 12B – a story‑focused vision model
Gemma 3 Starshine 12B is a 11.8B‑parameter model merged from Gemma‑3‑Glitter‑12B and Gemma‑3‑Confetti‑12B. It supports instruct format with an optional system role and includes a vision tower. The model is tuned for creative writing and role‑playing scenarios.
Good at
- Creative storytelling
- Role‑playing dialogue
- Instruction following
Limits
- No explicit license information
- Vision support only via mmproj files
- No mention of multilingual coverage
Best for
- Writing short stories
- Generating role‑play scripts
- Assisting with creative prompts
Who it’s for. Developers and writers who need a lightweight, story‑oriented LLM with vision capabilities. The model is suitable for local deployment using GGUF and llama.cpp.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 2.9 GB | 6.7 GB | Fits | Get file → | |
| IQ1_M | 3.2 GB | 6.9 GB | Fits | Get file → | |
| IQ2_XXS | 3.5 GB | 7.2 GB | Tight | Get file → | |
| IQ2_XS | 3.8 GB | 7.6 GB | Tight | Get file → | |
| IQ2_S | 4.0 GB | 7.7 GB | Tight | Get file → | |
| IQ2_M | 4.3 GB | 8.0 GB | Too big | Get file → | |
| Q2_K_S | 4.4 GB | 8.2 GB | Too big | Get file → | |
| Q2_K | 4.8 GB | 8.5 GB | Too big | Get file → | |
| IQ3_XXS | 4.8 GB | 8.5 GB | Too big | Get file → | |
| IQ3_XS | 5.2 GB | 8.9 GB | Too big | Get file → | |
| IQ3_S | 5.5 GB | 9.2 GB | Too big | Get file → | |
| Q3_K_S | 5.5 GB | 9.2 GB | Too big | Get file → | |
| IQ3_M | 5.7 GB | 9.4 GB | Too big | Get file → | |
| Q3_K_M | 6.0 GB | 9.7 GB | Too big | Get file → | |
| Q3_K_L | 6.5 GB | 10.2 GB | Too big | Get file → | |
| IQ4_XS | 6.6 GB | 10.3 GB | Too big | Get file → | |
| IQ4_NL | 6.9 GB | 10.6 GB | Too big | Get file → | |
| Q4_0 | 6.9 GB | 10.6 GB | Too big | Get file → | |
| Q4_K_S | 6.9 GB | 10.7 GB | Too big | Get file → | |
| Q4_K_M | 7.3 GB | 11.0 GB | Too big | Get file → | |
| Q4_1 | 7.6 GB | 11.3 GB | Too big | Get file → | |
| Q5_K_S | 8.2 GB | 12.0 GB | Too big | Get file → | |
| Q5_K_M | 8.4 GB | 12.2 GB | Too big | Get file → | |
| Q6_K | 9.7 GB | 13.4 GB | Too big | Get file → |
For 8 GB VRAM use IQ1_S (2.95 GB, 6.7 GB memory at 8 k context) or IQ1_M (3.16 GB, 6.9 GB). For 12 GB VRAM use Q4_K_M (7.3 GB, 11 GB) or Q5_K_S (8.23 GB, 12 GB). For 16 GB VRAM use Q6_K (9.66 GB, 13.4 GB). Estimates are approximate.
What GPU do you need for Gemma 3 Starshine 12B?
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: the best quant that fits is IQ2_M (4.3 GB file, about 8.0 GB in use).
- 12 GB VRAM: the best quant that fits is Q5_K_S (8.2 GB file, about 12.0 GB in use).
- 16 GB VRAM: the best quant that fits is Q6_K (9.7 GB file, about 13.4 GB in use).
Which Gemma 3 Starshine 12B quant should you choose?
Q4_K_M is the usual starting point for Gemma 3 Starshine 12B: it balances file size and quality well. Here it is a 7.3 GB file.
If memory is tight, the smallest file is IQ1_S at 2.9 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 Gemma 3 Starshine 12B
How much VRAM does Gemma 3 Starshine 12B need?
About 11.0 GB at Q4_K_M with an 8K context window. That is the 7.3 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 3 Starshine 12B on an 8 GB GPU?
Yes, with IQ2_M: the 4.3 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Gemma 3 Starshine 12B GGUF?
It depends on the quant: IQ1_S is 2.9 GB, IQ1_M is 3.2 GB, IQ2_XXS is 3.5 GB, IQ2_XS is 3.8 GB, IQ2_S is 4.0 GB, IQ2_M is 4.3 GB and 18 more.
What context length does Gemma 3 Starshine 12B support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 3.2 GB at 8K and 12.9 GB at 32K.
Where can I download Gemma 3 Starshine 12B GGUF?
The files are on Hugging Face in the mradermacher/Gemma-3-Starshine-12B-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
Can I run this model on 8 GB VRAM?
Yes, use IQ1_S or IQ1_M quantizations; they require about 6.7–6.9 GB memory at 8 k context.
Does this model support vision?
Yes, it includes a vision tower; mmproj files are provided in the static repository.
What is the context length?
The model was trained on 131072 tokens and supports that context length.