Modelpublic

abenzerps/Nex-N2.5-mini-MLX-6bit

sourceHugging Faceapache-2.0updated 15d agoView on Hugging Face

1likes607downloads

Model Card

Nex-N2.5-mini MLX — 6-bit

MLX 6-bit conversion of Nex-N2.5-mini, a sparse MoE language model for local inference, coding, reasoning, and long-context work. The source checkpoint supports a native context length of 262,144 tokens (256K).

Benchmarks

[image]

Benchmark results reported by Nex AI for the original Nex-N2.5 checkpoint and its upstream evaluation setup.

Release

Format	Quantization	Size
MLX safetensors	Affine 6-bit, group size 64	28.19 GB

This release contains the text-generation weights and tokenizer. It does not include MTP weights or a vision projector.

Usage

bash

pip install -U mlx-lm
mlx_lm.generate \
  --model . \
  --prompt "Explain why reproducible builds matter." \
  --max-tokens 512

Source

—Model: Nex-N2.5-mini
—Source revision: 87420286149d9cce9bd46cd335ef9bda33c37c1b
—License: Apache-2.0
—Checksums: SHA256SUMS.txt