Skip to content
Computer vision

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 moreDetails
• 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
Discuss Telegram 0

Will it run?

Working out the memory needs

This is a LoRA: it only runs on top of the base model harness-hub/Qwen3.8-27B-opencode-adapted. The base model's size is still being collected; the estimate will appear within a day.

Massed ComputeOpen Massed Compute

Run it on Massed Compute

The script downloads the model to the rented machine. How to run it is in the model card.

  1. 1. Rent a machine with a fitting GPU

    Open Massed Compute
  2. 2. Paste the script into the machine's terminal

    Connect over SSH (the Massed Compute panel shows the command) or open a terminal on the machine's desktop.

    HF_TOKEN / CIVITAI_TOKENThe script starts with token lines: paste yours between the quotes. The Hugging Face token is for gated models, the Civitai one for Civitai models.

    # netprojects/Qwen3.8-27B-opencode-adapted-MLX-adapter
    # ===== Tokens: paste yours between the quotes =====
    export HF_TOKEN=""        # huggingface.co/settings/tokens, for gated models
    # ==========================================
    mkdir -p ~/models
    curl -LsSf https://astral.sh/uv/install.sh | sh
    source "$HOME/.local/bin/env"
    uv tool install "huggingface_hub[cli]"
    hf download harness-hub/Qwen3.8-27B-opencode-adapted --local-dir ~/models/Qwen3.8-27B-opencode-adapted
    hf download netprojects/Qwen3.8-27B-opencode-adapted-MLX-adapter --local-dir ~/models/Qwen3.8-27B-opencode-adapted-MLX-adapter
    # The model is in ~/models. How to run it is in the model card (link above).
  3. 3. Use it

    The model is in ~/models. How to run it is in the model card (link above).

Stop the machine in the panel when you are done: it bills by the minute while it runs.

How to speed it up

Picked for this model type. Choose your hardware above to see what fits you exactly.

  • FlashAttention 44.0.0b40from November 18, 2026new release

    fastest exact attention on B200

    Kernels for Blackwell (beta). Exact attention without quantisation — fine for everything, LLMs included.

    How to enable: pip install flash-attn-4; vLLM and SGLang pick it up themselves.

    Earlier generations (2)
    • FlashAttention 3 — The Hopper (H100/H200) version with FP8.
    • FlashAttention 2 — The standard for RTX 30/40/50 and A100: exact attention without the memory cost of long contexts.
  • torch.compile2.15.0from October 28, 2026new release

    10–30% for free

    Compiles the model for your GPU. Slower first run, faster afterwards.

    How to enable: model = torch.compile(model); in ComfyUI the TorchCompileModel node.

Model family

Requires the base model

harness-hub/Qwen3.8-27B-opencode-adapted

This model is a LoRA / adapter. Download the base model first, then load this one on top.

  1. Qwen3.8-27Bfamily root
  2. Qwen3.8-27B-opencode-adapted
  3. Qwen3.8-27B-opencode-adapted-MLX-adapter

New posts about versions of Qwen3.8-27B (quants, finetunes, LoRAs) will show up under the bell.

Quantised versions 12All on Hugging Face
Fine-tunes 12All on Hugging Face
LoRAs and adapters 2All on Hugging Face

About the model

netprojects/Qwen3.8-27B-opencode-adapted-MLX-adapter
Author
netprojects
Category
Computer vision
Released
Posted

On NeyroLearn

Hugging Face

00

Ask AI about this model

Answered by Gemini 4 · the chat is kept only in this tab

Comments