harness-hub/Qwen3.8-27B-opencode-adapted (revision b4171c0) merged into
Qwen/Qwen3.8-27B (revision 3756181) and converted to MLX with mlx-vlm, vision
encoder and Qwen's MTP layer included. In this build the linear layers are quantized to 4-bit (affine, group 64). Size: 16.3 GB.
harness-hub trained this LoRA with reinforcement learning (AsyncGRPO in TRL) to be the model behind the OpenCode coding agent on software-engineering and terminal tasks. Their published results, under OpenCode with thinking off: SWE-bench Pro (hard 51) 35.3% → 51.0% and Terminal-Bench 2.1 46.4% → 52.4% against the base model, and with thinking off it matches the base model thinking at its highest effort while generating about a sixth of the tokens. See the original adapter card for the method, data and full results.
| Build | Size | Same next token as bf16 | KL vs bf16 |
|---|---|---|---|
| netprojects/Qwen3.8-27B-opencode-adapted-MLX-6bit (recommended) | 23.1 GB | 98.7% | 0.0014 |
| netprojects/Qwen3.8-27B-opencode-adapted-MLX-8bit | 30.0 GB | 99.2% | 0.0004 |
| netprojects/Qwen3.8-27B-opencode-adapted-MLX-4bit | 16.3 GB | 96.7% | 0.0203 |
| netprojects/Qwen3.8-27B-opencode-adapted-MLX-3bit | 13.8 GB | 93.4% | 0.0812 |
| netprojects/Qwen3.8-27B-opencode-adapted-MLX-bf16 | 55.6 GB | reference | reference |
| netprojects/Qwen3.8-27B-opencode-adapted-MLX-adapter | 638 MB | LoRA only, for mlx-lm | on any Qwen3.8-27B MLX build |
The 6-bit build is the recommended balance of size and fidelity; 8-bit is closest to bf16; 4-bit and 3-bit are for Macs with less memory (3-bit fits 24 GB Macs).
The adapter was trained and evaluated with thinking off, so keep it off. Serve the model with mlx-lm's OpenAI-compatible server:
pip install -U "mlx-lm>=0.32.2"
mlx_lm.server --model netprojects/Qwen3.8-27B-opencode-adapted-MLX-4bit --port 8000 \
--chat-template-args '{"enable_thinking": false}'
Add it to ~/.config/opencode/opencode.json:
{
"$schema": "https://opencode.ai/config.json",
"provider": {
"local": {
"npm": "@ai-sdk/openai-compatible",
"options": { "baseURL": "http://localhost:8000/v1", "apiKey": "dummy" },
"models": { "netprojects/Qwen3.8-27B-opencode-adapted-MLX-4bit": {} }
}
}
}
opencode run --model local/netprojects/Qwen3.8-27B-opencode-adapted-MLX-4bit "Find out why the tests in tests/test_parser.py fail and fix the bug."
Text only, with mlx-lm:
from mlx_lm import load, generate
model, tokenizer = load("netprojects/Qwen3.8-27B-opencode-adapted-MLX-4bit")
messages = [{"role": "user", "content": "Write a Python function that parses '1.5M' into bytes."}]
prompt = tokenizer.apply_chat_template(messages, add_generation_prompt=True, enable_thinking=False, tokenize=False)
print(generate(model, tokenizer, prompt=prompt, max_tokens=512))
With images, with mlx-vlm:
pip install -U "mlx-vlm>=0.7.11"
mlx_vlm.generate --model netprojects/Qwen3.8-27B-opencode-adapted-MLX-4bit --image screenshot.png \
--prompt "What error does this terminal show?" --max-tokens 300 # thinking stays off unless --enable-thinking
The tokenizer and chat template are harness-hub's files, unchanged (same vocabulary and tool-call format as Qwen3.8-27B).
Tool calls use Qwen's XML format (<tool_call><function=...><parameter=...>), which mlx-lm's server returns as
OpenAI tool_calls.
This build keeps Qwen3.8-27B's own multi-token-prediction (MTP) layer in model-mtp.safetensors, quantized to match
the build. The adapter does not change that layer, so it is Qwen's original MTP head. mlx-vlm uses it as a built-in
draft model when you pass the same repository as --draft-model:
mlx_vlm.generate --model netprojects/Qwen3.8-27B-opencode-adapted-MLX-4bit --draft-model netprojects/Qwen3.8-27B-opencode-adapted-MLX-4bit \
--draft-kind mtp --temperature 0 --max-tokens 512 --prompt "Write a Python function that checks whether a number is prime."
On this build MTP makes decoding about 1.9× faster with no extra download. The DSpine drafter with dspine-hybrid-mlx also works with these builds. Our measurements (greedy, thinking off, 5 prompts × 256 tokens from GSM8K, MATH-500, HumanEval, MBPP and MT-Bench, with other services running on the Mac, so treat them as indicative):
| Build | Plain | MTP (mlx-vlm 0.7.11) | DSpine v0.2.1 (4-bit drafter, block 5) |
|---|---|---|---|
| 4-bit | 33 tok/s | 62 tok/s (×1.91) | 73 tok/s (×2.29) |
| 6-bit | 20 tok/s | 21 tok/s (×1.04) | 60 tok/s (×2.72) |
| 8-bit | 17 tok/s | 37 tok/s (×2.15) | 54 tok/s (×3.03) |
Both methods check every drafted token with the full model. With greedy decoding the text matches plain decoding until a near-tie, where the batched check can round the other way, so long answers can diverge slightly.
These builds also run in Splash (1.7.0), which uses its own DFlash2 draft model for speculative decoding. Measured on the same 5 prompts × 256 tokens, thinking off, on 19 November 2026 with other models loaded on the Mac, so treat the speeds as indicative; text, tool calling and image input passed on every build:
| Build | Decode speed | End to end, incl. prompt | Tokens per cycle |
|---|---|---|---|
| 4-bit | 156 tok/s | 123 tok/s | 6.7 |
| 6-bit | 132 tok/s | 100 tok/s | 6.8 |
| 8-bit | 109 tok/s | 85 tok/s | 6.6 |
hf download netprojects/Qwen3.8-27B-opencode-adapted-MLX-4bit --local-dir Qwen3.8-27B-opencode-adapted-MLX
splash serve --model-dir Qwen3.8-27B-opencode-adapted-MLX --model local/qwen3.8-opencode --reasoning-effort none
Splash loads the quantized builds (4, 6 and 8-bit); it does not load bf16 MLX checkpoints.
On a MacBook Pro M5 Max (128 GB), 18 November 2026, with mlx 0.32.4, mlx-lm 0.32.2 and mlx-vlm 0.7.11.
W + 2.0 · B @ A rounded to bf16, checked element by element against an independent float64 computation; every other tensor is byte-identical to Qwen3.8-27B. The adapter does not touch the vision encoder or the Gated DeltaNet layers.bash and read tools; 8-bit, 6-bit, 4-bit each produced a well-formed bash tool call in Qwen's XML format.mtp.* weights (norms in mlx-vlm's stored form), quantized exactly like the rest of the build; each build loads normally in mlx-lm and mlx-vlm with the extra file present.The adapter is by harness-hub; the base model is Qwen3.8-27B by the Qwen Team, Alibaba Cloud. If you use the model, please cite their work (see the adapter card and the Qwen3.8-27B card).
Apache-2.0, as Qwen3.8-27B and the harness-hub adapter. LICENSE is the Apache-2.0 text from the Qwen3.8-27B repository
and NOTICE describes the conversion and credits harness-hub and the Qwen Team (Alibaba Cloud).
Published by NetProjects (Internet Projects Ltd). Not affiliated with Hugging Face, harness-hub or Alibaba.
More MLX builds from NetProjects: huggingface.co/netprojects · netprojects.com
model-00003-of-00003.safetensors 5.4 GBmodel-00002-of-00003.safetensors 5.4 GBmodel-00001-of-00003.safetensors 5.3 GBmodel-mtp.safetensors 239 MB