metadata
library_name: mlx
pipeline_tag: text-generation
license: mit
language:
- en
base_model: miromind-ai/MiroThinker-v1.0-8B
tags:
- agent
- open-source
- miromind
- deep-research
- mlx
johnsmith968530/miromind-ai-MiroThinker-v1.0-8B-MLX-8bit
This model johnsmith968530/miromind-ai-MiroThinker-v1.0-8B-MLX-8bit was converted to MLX format from miromind-ai/MiroThinker-v1.0-8B using mlx-lm version 0.28.3.
export MODEL1_MAJOR="miromind-ai"
export MODEL1_MINOR="MiroThinker-v1.0-8B"
export MODEL1_Q_BITS="8"
export MODEL1_DTS="$(date -z UTC +%Y%m%d_%H%M%SZ)"
echodo () { echo "$@" && "$@"; }
mkdir -p /tmp/mlx/lm/convert
# uv tool install -U mlx-lm
echodo time mlx_lm.convert \
--hf-path "$MODEL1_MAJOR/$MODEL1_MINOR" \
--mlx-path "/tmp/mlx/lm/convert/$MODEL1_DTS" \
--quantize \
--q-bits "$MODEL1_Q_BITS" \
--upload-repo \
"johnsmith968530/$MODEL1_MAJOR-$MODEL1_MINOR-MLX-${MODEL1_Q_BITS}bit"
# I tested the result using LM Studio 0.3.31
# on a MacBook Air, 13 inch, M4, 2025 with 32 GB unified memory
# macOS Tahoe 26.1.