SP

Sparkle 12B

SparkleGGUF by mradermacherUpdated 2025-04-20
Download on Hugging Face
Parameters11.8B
Context128K
Layers48
Architecturegemma3
Smallest quant2.9 GB
Quick answer

Sparkle 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.

Sparkle 12B – 11.8B‑parameter gemma3 model

Sparkle 12B is a 11.8B‑parameter gemma3 model trained on 131072 context tokens. It supports roleplay and is released under apache-2.0. The model is available in multiple GGUF quantizations.

Good at

  • Roleplay
  • Large context handling
  • Flexible quant options

Limits

  • No vision support
  • Large memory requirement for higher quants
  • No mixture of experts

Best for

  • Chatbot development
  • Interactive storytelling
  • Roleplay simulations

Who it’s for. Developers building conversational agents that need large context and roleplay capabilities. Researchers who require a gemma3 architecture with flexible quantization options.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S2.9 GB 6.7 GB
Fits Get file →
IQ1_M3.2 GB 6.9 GB
Fits Get file →
IQ2_XXS3.5 GB 7.2 GB
Tight Get file →
IQ2_XS3.8 GB 7.6 GB
Tight Get file →
IQ2_S4.0 GB 7.7 GB
Tight Get file →
IQ2_M4.3 GB 8.0 GB
Too big Get file →
Q2_K_S4.4 GB 8.2 GB
Too big Get file →
Q2_K4.8 GB 8.5 GB
Too big Get file →
IQ3_XXS4.8 GB 8.5 GB
Too big Get file →
IQ3_XS5.2 GB 8.9 GB
Too big Get file →
IQ3_S5.5 GB 9.2 GB
Too big Get file →
Q3_K_S5.5 GB 9.2 GB
Too big Get file →
IQ3_M5.7 GB 9.4 GB
Too big Get file →
Q3_K_M6.0 GB 9.7 GB
Too big Get file →
Q3_K_L6.5 GB 10.2 GB
Too big Get file →
IQ4_XS6.6 GB 10.3 GB
Too big Get file →
IQ4_NL6.9 GB 10.6 GB
Too big Get file →
Q4_06.9 GB 10.6 GB
Too big Get file →
Q4_K_S6.9 GB 10.7 GB
Too big Get file →
Q4_K_M7.3 GB 11.0 GB
Too big Get file →
Q4_17.6 GB 11.3 GB
Too big Get file →
Q5_K_S8.2 GB 12.0 GB
Too big Get file →
Q5_K_M8.4 GB 12.2 GB
Too big Get file →
Q6_K9.7 GB 13.4 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (6.7 GB) or IQ1_M (6.9 GB). If 12 GB VRAM is available, Q4_K_M (11 GB) or Q5_K_M (12.2 GB) are suitable. Larger quants need more memory and are not recommended for limited VRAM setups.

What GPU do you need for Sparkle 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 Sparkle 12B quant should you choose?

Q4_K_M is the usual starting point for Sparkle 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

Architecturegemma3
Parameters11.8B
Layers48
Trained context131,072 tokens
KV cache (fp16)384 KB per token

Source

Quantized bymradermacher
FamilySparkle
Licenseapache-2.0
Downloads (HF)801
Last updated2025-04-20

Frequently asked questions about Sparkle 12B

How much VRAM does Sparkle 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 Sparkle 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 Sparkle 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 Sparkle 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 Sparkle 12B GGUF?

The files are on Hugging Face in the mradermacher/Sparkle-12B-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 Sparkle 12B 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 Sparkle 12B on 8 GB VRAM?

Use IQ1_S or IQ1_M quantizations; they estimate 6.7–6.9 GB memory at 8k context.

Does Sparkle 12B support vision tasks?

No, the model has no vision capabilities.

What license applies to Sparkle 12B?

The model is released under the apache-2.0 license.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Sparkle models

All Sparkle →

Other medium models

All medium models →