Text Generation
GGUF
Rust
English
Portuguese
mark_engineer_v2_8b
mark-ai
systems-engineering
linux-kernel
cpp
c
reverse-engineering
robotics
electrical-engineering
mla
Mixture of Experts
mtp
ollama
custom_code
conversational
Instructions to use miceworks/Mark-Engineer-V2-8B 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 miceworks/Mark-Engineer-V2-8B 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 miceworks/Mark-Engineer-V2-8B:IQ4_NL # Run inference directly in the terminal: llama cli -hf miceworks/Mark-Engineer-V2-8B:IQ4_NL
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf miceworks/Mark-Engineer-V2-8B:IQ4_NL # Run inference directly in the terminal: llama cli -hf miceworks/Mark-Engineer-V2-8B:IQ4_NL
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 miceworks/Mark-Engineer-V2-8B:IQ4_NL # Run inference directly in the terminal: ./build/bin/llama cli -hf miceworks/Mark-Engineer-V2-8B:IQ4_NL
Use Docker
docker model run hf.co/miceworks/Mark-Engineer-V2-8B:IQ4_NL
- Llama new
- LM Studio
- Jan
- vLLM
How to use miceworks/Mark-Engineer-V2-8B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "miceworks/Mark-Engineer-V2-8B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "miceworks/Mark-Engineer-V2-8B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/miceworks/Mark-Engineer-V2-8B:IQ4_NL
- Ollama
How to use miceworks/Mark-Engineer-V2-8B with Ollama:
ollama run hf.co/miceworks/Mark-Engineer-V2-8B:IQ4_NL
- Unsloth Desktop
- Docker Model Runner
How to use miceworks/Mark-Engineer-V2-8B with Docker Model Runner:
docker model run hf.co/miceworks/Mark-Engineer-V2-8B:IQ4_NL
- Lemonade
How to use miceworks/Mark-Engineer-V2-8B with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull miceworks/Mark-Engineer-V2-8B:IQ4_NL
Run and chat with the model
lemonade run user.Mark-Engineer-V2-8B-IQ4_NL
List all available models
lemonade list
- Atomic Chat
Download training_metadata.json from miceworks/Mark-Engineer-V2-8B: direct link, hf CLI and curl.
- Browser
- Download file 345 Bytes
-
https://huggingface.co/miceworks/Mark-Engineer-V2-8B/resolve/main/training_metadata.json
- Command line
-
hf download hf://miceworks/Mark-Engineer-V2-8B/training_metadata.json
-
curl -L -o training_metadata.json https://huggingface.co/miceworks/Mark-Engineer-V2-8B/resolve/main/training_metadata.json
345 Bytes
| { | |
| "model_name": "Mark-Engineer-V2-8B-MoE", | |
| "total_steps": 5, | |
| "final_loss": 2.0099, | |
| "status": "CONVERGED", | |
| "completion_timestamp": "2026-10-26 21:23:57", | |
| "target_hardware": "NVIDIA GeForce RTX 2060 SUPER 8GB", | |
| "dataset_curriculum": "/home/thu12/hd_1tb/mark_training_hub/04_master_curriculum/mark_engineer_v2_8b_master_train.jsonl" | |
| } |