Instructions to use ConceptCountry/qwen-concept-27b 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 ConceptCountry/qwen-concept-27b 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 ConceptCountry/qwen-concept-27b:Q4_K_M # Run inference directly in the terminal: llama cli -hf ConceptCountry/qwen-concept-27b:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf ConceptCountry/qwen-concept-27b:Q4_K_M # Run inference directly in the terminal: llama cli -hf ConceptCountry/qwen-concept-27b: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 ConceptCountry/qwen-concept-27b:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama cli -hf ConceptCountry/qwen-concept-27b:Q4_K_M
Use Docker
docker model run hf.co/ConceptCountry/qwen-concept-27b:Q4_K_M
- Llama new
- LM Studio
- Jan
- Ollama
How to use ConceptCountry/qwen-concept-27b with Ollama:
ollama run hf.co/ConceptCountry/qwen-concept-27b:Q4_K_M
- Unsloth Desktop
- Pi
How to use ConceptCountry/qwen-concept-27b with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf ConceptCountry/qwen-concept-27b: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": "ConceptCountry/qwen-concept-27b:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use ConceptCountry/qwen-concept-27b with Docker Model Runner:
docker model run hf.co/ConceptCountry/qwen-concept-27b:Q4_K_M
- Lemonade
How to use ConceptCountry/qwen-concept-27b with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull ConceptCountry/qwen-concept-27b:Q4_K_M
Run and chat with the model
lemonade run user.qwen-concept-27b-Q4_K_M
List all available models
lemonade list
- Hermes Agent
How to use ConceptCountry/qwen-concept-27b with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf ConceptCountry/qwen-concept-27b: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 ConceptCountry/qwen-concept-27b:Q4_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use ConceptCountry/qwen-concept-27b with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf ConceptCountry/qwen-concept-27b: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 "ConceptCountry/qwen-concept-27b: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"
Qwen Concept 27B
Qwen3.8-27B with nine down-projections rewritten by weight-space programming. No gradient steps, no training data: the edit is derived from the model's own activations and compiled into nine weight matrices.
The model thinks less and scores higher. Against the unmodified base, on a pre-registered criterion: GPQA Diamond +4.3 [+1.8, +7.1], LiveCodeBench v6 +13.0, with thinking tokens down 27-54%.
The contribution is the control, not the edit. A norm-matched random edit โ same layers, same magnitude, different direction โ does nothing, and its confidence intervals straddle zero on every benchmark. That is what separates "this direction means something" from "perturbation helps".
Paper, data and the code that generates every number: https://concept.country/research/weight-space-programming
Formats
| folder | format | size | notes |
|---|---|---|---|
bf16/ |
bfloat16 | ~52 GB | full precision; every reported number comes from these weights |
fp8/ |
FP8_BLOCK | ~30 GB | matches Qwen's official FP8 layout |
nvfp4a16/ |
NVFP4 W4A16 | ~20 GB | NVFP4 weights, BF16 activations; Blackwell-class hardware |
gguf/ |
Q8_0 | ~27 GB | llama.cpp; the exact file the benchmarks ran on |
gguf/ |
Q4_K_M | ~16 GB | llama.cpp; quantized one hop from bf16, not from the Q8_0 |
The quantizations are deployment conveniences, not separately evaluated artifacts. Every number above is from bf16 weights served at Q8_0. Nothing here claims a 4-bit conversion preserves the effect โ that needs its own evaluation and has not had one.
Each folder carries a SHA256SUMS file.
Also available
Mirrored on the Concept Country registry, which speaks the HF Hub API:
HF_ENDPOINT=https://models.concept.country hf download ConceptCountry/qwen-concept-27b
Status
Experimental, under evaluation.
License
Apache-2.0, inherited from Qwen3.8-27B (Alibaba Cloud).
- Downloads last month
- 64,846
4-bit
8-bit