Instructions to use oN8WeJbq5Jo7Pk/hus1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use oN8WeJbq5Jo7Pk/hus1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="oN8WeJbq5Jo7Pk/hus1") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] pipe(text=messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("oN8WeJbq5Jo7Pk/hus1") model = AutoModelForMultimodalLM.from_pretrained("oN8WeJbq5Jo7Pk/hus1", device_map="auto") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] inputs = processor.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=256) print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use oN8WeJbq5Jo7Pk/hus1 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 oN8WeJbq5Jo7Pk/hus1:BF16 # Run inference directly in the terminal: llama cli -hf oN8WeJbq5Jo7Pk/hus1:BF16
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf oN8WeJbq5Jo7Pk/hus1:BF16 # Run inference directly in the terminal: llama cli -hf oN8WeJbq5Jo7Pk/hus1:BF16
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 oN8WeJbq5Jo7Pk/hus1:BF16 # Run inference directly in the terminal: ./build/bin/llama cli -hf oN8WeJbq5Jo7Pk/hus1:BF16
Use Docker
docker model run hf.co/oN8WeJbq5Jo7Pk/hus1:BF16
- Llama new
- LM Studio
- Jan
- vLLM
How to use oN8WeJbq5Jo7Pk/hus1 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "oN8WeJbq5Jo7Pk/hus1" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "oN8WeJbq5Jo7Pk/hus1", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/oN8WeJbq5Jo7Pk/hus1:BF16
- SGLang
How to use oN8WeJbq5Jo7Pk/hus1 with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "oN8WeJbq5Jo7Pk/hus1" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "oN8WeJbq5Jo7Pk/hus1", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "oN8WeJbq5Jo7Pk/hus1" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "oN8WeJbq5Jo7Pk/hus1", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Ollama
How to use oN8WeJbq5Jo7Pk/hus1 with Ollama:
ollama run hf.co/oN8WeJbq5Jo7Pk/hus1:BF16
- Unsloth Desktop
- Pi
How to use oN8WeJbq5Jo7Pk/hus1 with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf oN8WeJbq5Jo7Pk/hus1:BF16
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": "oN8WeJbq5Jo7Pk/hus1:BF16" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use oN8WeJbq5Jo7Pk/hus1 with Docker Model Runner:
docker model run hf.co/oN8WeJbq5Jo7Pk/hus1:BF16
- Lemonade
How to use oN8WeJbq5Jo7Pk/hus1 with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull oN8WeJbq5Jo7Pk/hus1:BF16
Run and chat with the model
lemonade run user.hus1-BF16
List all available models
lemonade list
- Hermes Agent
How to use oN8WeJbq5Jo7Pk/hus1 with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf oN8WeJbq5Jo7Pk/hus1:BF16
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 oN8WeJbq5Jo7Pk/hus1:BF16
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use oN8WeJbq5Jo7Pk/hus1 with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf oN8WeJbq5Jo7Pk/hus1:BF16
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 "oN8WeJbq5Jo7Pk/hus1:BF16" \ --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 Trim B7
We ran out of compute while finishing the broader FFN pruning study. This release packages the complete, verified block-7-removed B7 checkpoint so the work is available instead of being lost. No unfinished FFN width cut is merged into these weights.
Support the project
Donations will be used to fund the project and AI subscriptions.
Donate here: https://buymeacoffee.com/dgresesjr
Included weights
| File / directory | Format | Size |
|---|---|---|
| Root safetensors shards | HF BF16, 18 shards | 50.478 GB of tensors |
gguf/qwen3.8-27b-trim-b7-bf16.gguf |
GGUF BF16 | 49.567 GB |
gguf/qwen3.8-27b-trim-b7-q4_k_m.gguf |
GGUF Q4_K_M | 15.324 GB |
The Q4_K_M file is the practical option for a 24 GB GPU. The BF16 checkpoint requires more than 50 GB of weight memory.
Model details
- 25.239B tensor elements
- 60 main layers, plus one MTP layer in GGUF
- Original block 7 (layers 28-31) physically removed and later layers reindexed
- Three linear-attention layers followed by one full-attention layer
- Hidden size: 5,120
- FFN intermediate width: 17,408
- 1.522B parameters and 3.044 GB of BF16 tensors removed relative to the trimmed input
Validation
- All 1,146 HF tensors and every FFN shape verified
- B7 loss matched the earlier block-7 skip run within 0.00108 maximum bucket difference
- B7 hard-benchmark result: 88/160 (math 22/40, code 40/40, tools 12/40, knowledge 14/40)
- Corrected original-model tools baseline: 13/40
- Q4_K_M loaded with full GPU offload on an RTX 3090 using llama.cpp b12359 and correctly answered
17 + 25 = 42
Q4 usage
llama-completion \
-m qwen3.8-27b-trim-b7-q4_k_m.gguf \
-p "17 + 25 =" -n 128 --temp 0 -ngl 99 -c 512 -t 6 -no-cnv
FFN checkpoints
The 10%, 20%, and 30% repair plans reached 38/60, 40/60, and 33/60 layers respectively before compute ran out. They are preserved separately as checkpoints, not complete models, and are intentionally not included in this deployable checkpoint.
- Downloads last month
- 204
