Maple Preview needs about 6.3 GB of memory at TQ1_0 (a 5.4 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 4 quants, from 5.0 GB (TQ1_0) to 6.3 GB (TQ2_0). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.
Maple Preview: 20B reasoning model optimized for on‑device inference
Maple Preview is a 20.2B parameter model built for efficient local use. It supports 131072 context tokens and is designed for reasoning and coding tasks. The model is released under the MIT license.
Good at
- Reasoning
- Coding
- Large context support
Limits
- No vision support
- Requires 8‑k context for memory estimates
- No agentic benchmark focus
Best for
- Local reasoning tasks
- Code generation on limited hardware
- Long‑form text analysis
Who it’s for. Developers and researchers who need a lightweight reasoning model for on‑device inference. The model is suitable for users with moderate VRAM and RAM who want to run a 20B model locally.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| TQ1_0 | 5.0 GB | 5.9 GB | Fits | Get file → | |
| TQ1_0 | 5.4 GB | 6.3 GB | Fits | Get file → | |
| TQ2_0 | 5.9 GB | 6.8 GB | Fits | Get file → | |
| TQ2_0 | 6.3 GB | 7.3 GB | Tight | Get file → |
For 8‑GB VRAM, use the TQ1_0 variant at 4.98 GB (est. 5.9 GB memory). If 12‑GB VRAM is available, the 5.43 GB TQ1_0 or 5.9 GB TQ2_0 variants are suitable. Larger VRAM allows the 6.35 GB TQ2_0 for higher speed.
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: the best quant that fits is TQ1_0 (5.0 GB file, about 5.9 GB in use).
- 8 GB VRAM: the best quant that fits is TQ2_0 (6.3 GB file, about 7.3 GB in use).
Which Maple Preview quant should you choose?
TQ1_0 (5.4 GB) is the middle option in this repository. Lower bit counts mean smaller files and more quality loss.
If memory is tight, the smallest file is TQ1_0 at 5.0 GB, with the quality trade-offs that come with fewer bits. Lower bit counts mean smaller files and more quality loss.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Maple Preview
How much VRAM does Maple Preview need?
About 6.3 GB at TQ1_0 with an 8K context window. That is the 5.4 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 6.3 GB file needs about 7.3 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: TQ1_0 is 5.0 GB, TQ1_0 is 5.4 GB, TQ2_0 is 5.9 GB, TQ2_0 is 6.3 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 deepgrove/maple-preview-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 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 4.98 GB TQ1_0 variant uses approximately 5.9 GB memory at 8k context, fitting within 8 GB VRAM.
Does Maple Preview support vision tasks?
No, the model does not include vision capabilities.