Instructions to use netprojects/Qwen3.8-27B-opencode-adapted-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use netprojects/Qwen3.8-27B-opencode-adapted-GGUF with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf netprojects/Qwen3.8-27B-opencode-adapted-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf netprojects/Qwen3.8-27B-opencode-adapted-GGUF:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf netprojects/Qwen3.8-27B-opencode-adapted-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf netprojects/Qwen3.8-27B-opencode-adapted-GGUF:Q4_K_M
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf netprojects/Qwen3.8-27B-opencode-adapted-GGUF:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama cli -hf netprojects/Qwen3.8-27B-opencode-adapted-GGUF:Q4_K_M
Use Docker
docker model run hf.co/netprojects/Qwen3.8-27B-opencode-adapted-GGUF:Q4_K_M
- Llama new
- LM Studio
- Jan
- vLLM
How to use netprojects/Qwen3.8-27B-opencode-adapted-GGUF with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "netprojects/Qwen3.8-27B-opencode-adapted-GGUF" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "netprojects/Qwen3.8-27B-opencode-adapted-GGUF", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker
docker model run hf.co/netprojects/Qwen3.8-27B-opencode-adapted-GGUF:Q4_K_M
- Ollama
How to use netprojects/Qwen3.8-27B-opencode-adapted-GGUF with Ollama:
ollama run hf.co/netprojects/Qwen3.8-27B-opencode-adapted-GGUF:Q4_K_M
- Unsloth Desktop
- Pi
How to use netprojects/Qwen3.8-27B-opencode-adapted-GGUF with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf netprojects/Qwen3.8-27B-opencode-adapted-GGUF:Q4_K_M
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:9931/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "netprojects/Qwen3.8-27B-opencode-adapted-GGUF:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use netprojects/Qwen3.8-27B-opencode-adapted-GGUF with Docker Model Runner:
docker model run hf.co/netprojects/Qwen3.8-27B-opencode-adapted-GGUF:Q4_K_M
- Lemonade
How to use netprojects/Qwen3.8-27B-opencode-adapted-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull netprojects/Qwen3.8-27B-opencode-adapted-GGUF:Q4_K_M
Run and chat with the model
lemonade run user.Qwen3.8-27B-opencode-adapted-GGUF-Q4_K_M
List all available models
lemonade list
- Hermes Agent
How to use netprojects/Qwen3.8-27B-opencode-adapted-GGUF with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf netprojects/Qwen3.8-27B-opencode-adapted-GGUF:Q4_K_M
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:9931/v1 hermes config set model.default netprojects/Qwen3.8-27B-opencode-adapted-GGUF:Q4_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use netprojects/Qwen3.8-27B-opencode-adapted-GGUF with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf netprojects/Qwen3.8-27B-opencode-adapted-GGUF:Q4_K_M
Configure OpenClaw
# Install OpenClaw: npm install -g openclaw@latest # Register the local server and set it as the default model: openclaw onboard --non-interactive --mode local \ --auth-choice custom-api-key \ --custom-base-url http://127.0.0.1:9931/v1 \ --custom-model-id "netprojects/Qwen3.8-27B-opencode-adapted-GGUF:Q4_K_M" \ --custom-provider-id llama-cpp \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
Qwen3.8-27B-opencode-adapted GGUF
harness-hub/Qwen3.8-27B-opencode-adapted (revision b4171c0) 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-opencode-F16.gguf adds image input.
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% โ 51.0% and Terminal-Bench 2.1 46.4% โ 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.
| File | Size | Same next token as BF16 | Mean KL divergence |
|---|---|---|---|
| Qwen3.8-27B-opencode-Q6_K.gguf (recommended) | 22.4 GB | 98.7% | 0.0197 |
| Qwen3.8-27B-opencode-Q8_0.gguf | 29.0 GB | 99.5% | 0.0002 |
| Qwen3.8-27B-opencode-Q4_K_M.gguf | 16.8 GB | 94.2% | 0.0689 |
| Qwen3.8-27B-opencode-Q3_K_M.gguf | 13.5 GB | 92.9% (vs Q8_0) | 0.0883 (vs Q8_0) |
| Qwen3.8-27B-opencode-IQ3_XXS.gguf | 11.4 GB | 91.0% (vs Q8_0) | 0.1356 (vs Q8_0) |
| Qwen3.8-27B-opencode-IQ2_M.gguf | 10.2 GB | 89.6% (vs Q8_0) | 0.1709 (vs Q8_0) |
| mmproj-Qwen3.8-27B-opencode-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 and the smaller Q3_K_M, IQ3_XXS, IQ2_M files are for machines with less memory. For Apple Silicon there are also MLX builds.
Use with OpenCode
The adapter was trained and evaluated with thinking off, so keep it off:
hf download netprojects/Qwen3.8-27B-opencode-adapted-GGUF Qwen3.8-27B-opencode-Q6_K.gguf mmproj-Qwen3.8-27B-opencode-F16.gguf --local-dir .
llama-server -m Qwen3.8-27B-opencode-Q6_K.gguf -mm mmproj-Qwen3.8-27B-opencode-F16.gguf \
--jinja --chat-template-kwargs '{"enable_thinking": false}' \
--spec-type draft-mtp -c 65536 --port 8000 --alias qwen3.8-opencode
--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 ~/.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": { "qwen3.8-opencode": {} }
}
}
}
opencode run --model local/qwen3.8-opencode "Find out why the tests in tests/test_parser.py fail and fix the bug."
Faster decoding with MTP
Measured with llama-server (Homebrew llama.cpp, commit b1b770d90) on a MacBook Pro M5 Max: greedy, thinking off, 5 prompts ร 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 | 27 tok/s | 53 tok/s (ร1.97) | 77% |
| Q6_K | 22 tok/s | 46 tok/s (ร2.07) | 73% |
| Q8_0 | 18 tok/s | 43 tok/s (ร2.36) | 74% |
With Splash
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 ร 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 | 144 tok/s | 111 tok/s | 6.6 |
| Q6_K | 129 tok/s | 98 tok/s | 6.9 |
| Q8_0 | 105 tok/s | 85 tok/s | 6.6 |
splash serve --model-dir Qwen3.8-27B-opencode-Q6_K.gguf --mmproj mmproj-Qwen3.8-27B-opencode-F16.gguf \
--model local/qwen3.8-opencode --reasoning-effort none
Smaller files
Q3_K_M, IQ3_XXS, IQ2_M were added on 19 November 2026. They were quantized from our Q8_0 file with an importance matrix (llama-imatrix on the Q8_0, English news text and MIT-licensed Python code, 512-token chunks). The MTP layer is kept at Q4_K in the IQ files, because the importance matrix does not cover it. Same next token and KL divergence for these files are measured against the Q8_0 file on the same 12 prompts. With llama-server (thinking off, with mmproj) each answered a short question correctly, produced a well-formed tool call and described the test image; three short Python tasks run against asserts: Q3_K_M 3/3 coding, IQ3_XXS 3/3 coding, IQ2_M 3/3 coding.
What was checked
On a MacBook Pro M5 Max (128 GB), 18 November 2026.
- Merge. All 256 adapted modules (q, k, v, o in the 16 full-attention layers; gate, up, down in all 64 layers)
equal
W + 2.0 ยท B @ Arounded to bf16, checked element by element; every other tensor, including the MTP layer and the vision encoder, is byte-identical to Qwen3.8-27B. - Quantization. Each file was compared with the BF16 GGUF using llama-perplexity's KL-divergence mode on the chat-formatted outputs of 12 short prompts (table above).
- llama-server (thinking off, with mmproj): on Q8_0, Q6_K and Q4_K_M a short arithmetic question was answered
correctly, an agent-style prompt with
bashandreadtools produced a well-formedbashtool call, and a test image was described correctly (red square, blue circle). - Source files. Every file of both pinned upstream revisions matches the Hub's SHA-256 hashes.
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.
Credits
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).
License
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 ยท netprojects.com
- Downloads last month
- 891
2-bit
3-bit
4-bit
6-bit
8-bit
Model tree for netprojects/Qwen3.8-27B-opencode-adapted-GGUF
Base model
Qwen/Qwen3.8-27B