This repository contains an enhanced oQ8e MLX quantization of deepgrove/maple-preview, converted from the BF16 safetensors with oMLX.
This MLX quant upload
Approximately 21.5 GB for the complete local model directory (21,497,386,683 bytes).
Uses a 1,024-sample, 512-token enhanced iMatrix calibration.
All quantized tensors are 8-bit.
The 24 MoE router matrices and all normalization weights remain BF16.
lm_head and model.word_embeddings are 8-bit.
Requires custom-code loading (trust_remote_code=True). In oMLX, enable Trust Remote Code for this model.
This is an MLX conversion for local inference on Apple Silicon. Please follow the base model's MIT license and usage terms.
Recommended generation settings
Maple is a reasoning-heavy model and may spend a substantial part of its response budget thinking. For the OpenAI-compatible API or oMLX UI, start with:
These sampler values match DeepGrove's Maple llama.cpp setup. The model declares a native 131,072-token context window and does not require RoPE/YARN scaling for that window. Actual usable context may be lower on systems constrained by KV-cache memory; do not assume that extending beyond 131,072 tokens is supported.
Base model description
Maple-Preview
DeepGrove · 2026
Today we introduce Maple-Preview, an open-source 20B-A1B ternary-weight reasoning LLM. Maple-Preview has SOTA reasoning for its weight class and is even competitive with larger models. It solves IMO-level problems and runs at 200+ tokens/sec on a Mac mini M4, 5–16× faster than efficient models like Gemma 4, Qwen3.5, and gpt-oss.
20B-A1B Model
218 tok/s M4 Mac mini
5.31 GB Checkpoint
131,072 Token context
Maple-Preview speed and performance frontier
[!NOTE]
The included Transformers implementation depends on Triton and FlashAttention
and is intended for a compatible CUDA environment. The reported Apple Silicon
result uses a separate on-device runtime.
Architecture
Maple-Preview is a 20B-A1B reasoning model designed from the start for efficient on-device inference. It utilizes a 24-layer, 256-expert (8 active) configuration with 3:1 SWA-512:GA attention.
Evaluation
On benchmarks, Maple-Preview sets a new point on the Pareto frontier for both memory-to-performance and speed-to-performance, demonstrating its strong reasoning capabilities. However, we note that this preview is focused primarily on raw reasoning and, as such, may underperform on agentic benchmarks. We intend to continue improving general performance through extended training before Maple's full release.
Benchmark score comparison
Capability comparison using the dense output head across LCBv6, AIME 2026, HMMT 2026, and GPQA-D.
Limitations
This preview received minimal post-training for agentic tasks and only
small-scale general reinforcement learning.
