harness-hub/Qwen3.8-27B-pi-adapted (revision e786f84) merged into
Qwen/Qwen3.8-27B (revision 3756181) and converted to GGUF for llama.cpp:
ready-to-run files, no --lora needed. Every file keeps Qwen's multi-token-prediction (MTP) layer, so llama-server can
use it for faster decoding, and mmproj-Qwen3.8-27B-pi-F16.gguf adds image input.
harness-hub trained this LoRA with reinforcement learning (AsyncGRPO in TRL) to be the model behind the pi coding agent on software-engineering and terminal tasks. Their published results, under pi with thinking off: Terminal-Bench 2.1 39.5% → 55.8% and SWE-bench Pro (hard 51) 29.4% → 62.7% against the base model, with 55-64% fewer tool calls per task. See the original adapter card for the method, data and full results.
| File | Size | Same next token as BF16 | Mean KL divergence |
|---|---|---|---|
| Qwen3.8-27B-pi-Q6_K.gguf (recommended) | 22.4 GB | 98.4% | 0.0038 |
| Qwen3.8-27B-pi-Q8_0.gguf | 29.0 GB | 99.2% | 0.0003 |
| Qwen3.8-27B-pi-Q4_K_M.gguf | 16.8 GB | 94.2% | 0.0595 |
| mmproj-Qwen3.8-27B-pi-F16.gguf | 0.9 GB | vision projector |
Q6_K is the recommended balance of size and fidelity; Q8_0 is closest to the BF16 weights, Q4_K_M is the smallest. For Apple Silicon there are also MLX builds.
The adapter was trained and evaluated with thinking off, so keep it off:
hf download netprojects/Qwen3.8-27B-pi-adapted-GGUF Qwen3.8-27B-pi-Q6_K.gguf mmproj-Qwen3.8-27B-pi-F16.gguf --local-dir .
llama-server -m Qwen3.8-27B-pi-Q6_K.gguf -mm mmproj-Qwen3.8-27B-pi-F16.gguf \
--jinja --chat-template-kwargs '{"enable_thinking": false}' \
--spec-type draft-mtp -c 65536 --port 8000 --alias qwen3.8-pi
--spec-type draft-mtp turns on the built-in MTP layer; leave it out for plain decoding, and leave out -mm if you
do not need images. Then add the server to ~/.pi/agent/models.json:
{
"providers": {
"local": {
"baseUrl": "http://localhost:8000/v1",
"api": "openai-completions",
"apiKey": "dummy",
"models": [{ "id": "qwen3.8-pi" }]
}
}
}
"api": "openai-completions" matters: the adapter was trained and evaluated with the Chat Completions API.
pi --provider local --model qwen3.8-pi --print "Find out why the tests in tests/test_parser.py fail and fix the bug."
Measured with llama-server (Homebrew llama.cpp, commit b1b770d90) on a MacBook Pro M5 Max: 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 the speeds as indicative.
| File | Plain | --spec-type draft-mtp |
Drafts accepted |
|---|---|---|---|
| Q4_K_M | 28 tok/s | 52 tok/s (×1.86) | 76% |
| Q6_K | 22 tok/s | 45 tok/s (×2.01) | 72% |
| Q8_0 | 18 tok/s | 44 tok/s (×2.41) | 75% |
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:
| File | Decode speed | End to end, incl. prompt | Tokens per cycle |
|---|---|---|---|
| Q4_K_M | 165 tok/s | 128 tok/s | 6.7 |
| Q6_K | 132 tok/s | 100 tok/s | 6.9 |
| Q8_0 | 109 tok/s | 84 tok/s | 6.9 |
splash serve --model-dir Qwen3.8-27B-pi-Q6_K.gguf --mmproj mmproj-Qwen3.8-27B-pi-F16.gguf \
--model local/qwen3.8-pi --reasoning-effort none
On a MacBook Pro M5 Max (128 GB), 18 November 2026.
W + 2.0 · B @ A rounded to bf16, checked element by element; every other tensor, including the MTP layer and
the vision encoder, is byte-identical to Qwen3.8-27B.bash and read tools produced a well-formed bash tool call, and a test
image was described correctly (red square, blue circle).Converted with llama.cpp's convert_hf_to_gguf.py at commit 8642541b2 and quantized with llama-quantize from Homebrew
llama.cpp (commit b1b770d90). The tokenizer and chat template are harness-hub's files, embedded unchanged.
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 builds from NetProjects: huggingface.co/netprojects · netprojects.com
harness-hub/Qwen3.8-27B-pi-adapted