Outlier-Ai/Qwen2.5-Coder-14B-Instruct-MLX-4bit

Qwen2.5-Coder-14B-Instruct — MLX 4-bit

4-bit MLX conversion of Qwen2.5-Coder-14B-Instruct for Apple Silicon. Runs natively on M1, M2, M3, and M4 Macs via mlx_lm. Faithful port of the upstream weights — no fine-tuning, no merge.

Quick facts

• Upstream base: Qwen2.5-Coder-14B-Instruct
• Format: MLX 4-bit (mlx_lm.convert --q-bits 4 --q-group-size 64)
• License: apache-2.0
• Use case: code
• Runtime: mlx-lm, LM Studio, Jan, Outlier desktop app
• Publisher: Outlier-Ai (solo, Mac-native AI platform)

Quickstart (mlx-lm)

pip install -U mlx-lm
python -m mlx_lm.generate \
  --model Outlier-Ai/Qwen2.5-Coder-14B-Instruct-MLX-4bit \
  --prompt "Write a haiku about compilers." \
  --max-tokens 256

Quickstart (LM Studio)

Search for Outlier-Ai/Qwen2.5-Coder-14B-Instruct-MLX-4bit, then Load and chat.

Quickstart (Outlier desktop app)

One-click install from outlier.host. Listed in the library picker under code.

Why this repo exists

This is a canonically-named twin of Outlier-Ai/Outlier-Coder-Qwen25-14B-MLX-4bit. Same weights, same quant, different name. The branded repo carries the Outlier identity; this one carries the upstream identity so it's findable via searches like "qwen2.5-coder-14b-instruct 4bit mlx". Use whichever path you came across — both point to the same files.

Provenance

• Converted via mlx_lm.convert --q-bits 4 --q-group-size 64
• Source: Qwen2.5-Coder-14B-Instruct
• Date produced: 2026-04-19 (Day 19)
• Conversion factory: Outlier MEGA-INFINITE phase3

Related

• Branded twin (same weights): Outlier-Ai/Outlier-Coder-Qwen25-14B-MLX-4bit
• Outlier org on HuggingFace: Outlier-Ai
• Desktop app: outlier.host
• Founders lifetime ($200, 500-seat cap): buy.polar.sh
• Discord: discord.gg/Hapennmdn9

Collections

• Outlier for Apple Silicon (MLX): huggingface.co/collections/Outlier-Ai/outlier-consumer-edition-69e2fb4a0df119ea1747275e
• Outlier Research MoE: huggingface.co/collections/Outlier-Ai/outlier-research-69e2fb3a71984614b3c7a279
• Outlier Server V3.2: huggingface.co/collections/Outlier-Ai/outlier-server-v32-69e2fb4b71984614b3c7a4a3

Attribution

Base model by the upstream author (see Qwen2.5-Coder-14B-Instruct). Outlier contributes the MLX 4-bit conversion and desktop-app packaging. Capability credit for the base belongs entirely to upstream.

License

Redistributed under the upstream license: apache-2.0. Respect the terms of Qwen2.5-Coder-14B-Instruct when using this conversion.