Qwen3.8-27B-opencode-adapted MLX adapter
an Apple Silicon adapter for running the language model
2 min readupdated
This release is a LoRA (a lightweight add-on for a base model) in the mlx-lm library format, built to run Qwen3.8-27B on Apple Silicon Macs. Trained with reinforcement learning for software engineering and terminal workflows, the adapter turns the base model into a capable coding assistant without loading a full set of weights into memory. It's geared toward developers running advanced LLMs (large language models) locally on a Mac.
Key features
- mlx-lm format: rank 32, scale 2.0, and a 638 MB file size for smooth integration into the MLX ecosystem.
- Trained with reinforcement learning (AsyncGRPO in TRL) for specialized coding tasks.
- Compatible with the Qwen/Qwen3.8-27B base model and its quantized versions.
- Hot-swappable adapters on top of a single shared base model.
What you can do
- Run a local coding and command-line assistant paired with OpenCode.
- Integrate the adapter into Python scripts via the mlx-lm library.
- Spin up a local API server for code generation on your Mac.
Example
from huggingface_hub import snapshot_download
from mlx_lm import load, generate
adapter = snapshot_download("netprojects/Qwen3.8-27B-opencode-adapted-MLX-adapter")
model, tokenizer = load("mlx-community/Qwen3.8-27B-4bit", adapter_path=adapter)
prompt = tokenizer.apply_chat_template([{"role": "user", "content": "Hello"}], add_generation_prompt=True,
enable_thinking=False, tokenize=False)
print(generate(model, tokenizer, prompt=prompt, max_tokens=200))Read more
Details• SWE-bench Pro (hard 51): up from 35.3% to 51.0%
• Terminal-Bench 2.1: up from 46.4% to 52.4%
• License: Apache-2.0
• Adapter size: 638 MB










Comments