MA

Maple Preview

MapleGGUF by phantomic12Updated 2026-08-30
Download on Hugging Face
Parameters20.2B
Context128K
Layers24
Architecturemaple
Smallest quant5.9 GB
Quick answer

Maple Preview needs about 6.8 GB of memory at TQ2_0 (a 5.9 GB file) with an 8K context window, so it fits on a 8 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.

20B-A1B ternary-weight reasoning LLM

Maple Preview is a 20B-A1B ternary-weight MoE model with 131,072 token context. It focuses on efficient on-device inference and strong reasoning performance. The model is released under the MIT license.

Good at

  • Reasoning
  • Tools integration
  • Fast on-device inference

Limits

  • No vision support
  • Limited agentic training
  • Large memory requirement

Best for

  • Solving IMO-level problems
  • High-speed reasoning on CPUs
  • Inference on AMD Ryzen AI NPUs

Who it’s for. Developers needing a lightweight reasoning model for on-device use. Researchers testing MoE architectures and reasoning benchmarks may also find it useful.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
TQ2_05.9 GB 6.8 GB
Fits Get file →

The only available quant is TQ2_0, file size 5.9 GB. It requires approximately 6.8 GB of RAM at 8k context. For systems with 8 GB VRAM, this quant is suitable. If more memory is available, the same quant can be used for larger contexts.

What GPU do you need for Maple Preview?

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 TQ2_0 (5.9 GB file, about 6.8 GB in use).

Which Maple Preview quant should you choose?

TQ2_0 (5.9 GB) is the middle option in this repository. Lower bit counts mean smaller files and more quality loss.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturemaple
Parameters20.2B (approximate, mixture of experts)
Layers24
Trained context131,072 tokens
KV cache (fp16)48 KB per token

Source

Quantized byphantomic12
FamilyMaple
Licensemit
Downloads (HF)572
Last updated2026-08-30

Frequently asked questions about Maple Preview

How much VRAM does Maple Preview need?

About 6.8 GB at TQ2_0 with an 8K context window. That is the 5.9 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 Maple Preview on an 8 GB GPU?

Yes, with TQ2_0: the 5.9 GB file needs about 6.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Maple Preview GGUF?

It depends on the quant: TQ2_0 is 5.9 GB.

What context length does Maple Preview support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.6 GB at 32K.

Where can I download Maple Preview GGUF?

The files are on Hugging Face in the phantomic12/maple-preview-20b-q4nx repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Maple Preview use?

Hugging Face lists the license as mit. 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 Maple Preview on 8 GB VRAM?

Yes, the TQ2_0 quant uses about 6.8 GB of RAM at 8k context, fitting within 8 GB VRAM.

Does Maple Preview support vision tasks?

No, the model has no vision capabilities.

Other GGUFs of maple-preview

Similar models

Browse all →

More Maple models

All Maple →

Other medium models

All medium models →