Maple Preview — Hardware Requirements & GPU Compatibility
ChatReasoning
Maple Preview is a 20.2B-parameter open language model from deepgrove. It supports a context window of up to 131,072 tokens. At BF16 it needs about 40.83 GB of VRAM — see which GPUs and Macs can run it below.
6.6K downloads
384 likesSpecifications
- Publisher
- deepgrove
- Parameters
- 20.2B
- Architecture
- MapleForCausalLM
- Context Length
- 131,072 tokens
- Vocabulary Size
- 151,936
- Release Date
- 2026-08-04
- License
- MIT
Get Started
HuggingFace
How Much VRAM Does Maple Preview Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16est. | 16.00 | 40.8 GB | 47.2 GB | 40.43 GB | Brain floating point 16 — preferred for training |
est.= calculated VRAM estimate; no published GGUF file found for that quantization yet. Other rows are verified against real community uploads.
Which GPUs Can Run Maple Preview?
BF16 · 40.8 GBMaple Preview (BF16) requires 40.8 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 54+ GB is recommended. Using the full 131K context window can add up to 6.3 GB, bringing total usage to 47.2 GB. No single GPU has enough memory — multi-GPU or cluster setups are needed.
Which Devices Can Run Maple Preview?
BF16 · 40.8 GB27 devices with unified memory can run Maple Preview, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, MacBook Pro 16" M4 Max (48 GB).
Runs great
— Plenty of headroom
Frequently Asked Questions
- How much VRAM does Maple Preview need?
Maple Preview requires 40.8 GB of VRAM at BF16. Full 131K context adds up to 6.3 GB (47.2 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 20.2B × 16 bits ÷ 8 = 40.4 GB
KV Cache + Overhead ≈ 0.4 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 6.8 GB (at full 131K context)
VRAM usage by quantization
BF1640.8 GBBF16 + full context47.2 GB- Can NVIDIA GeForce RTX 5090 run Maple Preview?
No — Maple Preview requires at least 40.8 GB at BF16, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
- Can I run Maple Preview on a Mac?
Maple Preview requires at least 40.8 GB at BF16, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.
- Can I run Maple Preview locally?
Yes — Maple Preview can run locally on consumer hardware. At BF16 quantization it needs 40.8 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Maple Preview?
At BF16, Maple Preview can reach ~118 tok/s on AMD Instinct MI350X. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: NVIDIA B200 → 8000 ÷ 40.8 × 0.65 = ~127 tok/s
Estimated speed at BF16 (40.8 GB)
~127 tok/s~127 tok/s~118 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Maple Preview?
At BF16, the download is about 40.43 GB.
- Which GPUs can run Maple Preview?
No single consumer GPU has enough VRAM to run Maple Preview at BF16 (40.8 GB). Multi-GPU or professional hardware is required.
- Which devices can run Maple Preview?
27 devices with unified memory can run Maple Preview at BF16 (40.8 GB), including ASUS Ascent GX10, Asus ROG Flow Z13 (2025, Ryzen AI Max+ 395, 128 GB), Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.