Instructions to use miceworks/Mark-Engineer-302M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use miceworks/Mark-Engineer-302M 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-302M:IQ4_NL
# Run inference directly in the terminal:
llama cli -hf miceworks/Mark-Engineer-302M: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-302M:IQ4_NL
# Run inference directly in the terminal:
llama cli -hf miceworks/Mark-Engineer-302M:IQ4_NL

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf miceworks/Mark-Engineer-302M:IQ4_NL
# Run inference directly in the terminal:
./llama-cli -hf miceworks/Mark-Engineer-302M:IQ4_NL

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf miceworks/Mark-Engineer-302M:IQ4_NL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf miceworks/Mark-Engineer-302M:IQ4_NL

Use Docker

docker model run hf.co/miceworks/Mark-Engineer-302M:IQ4_NL

Llama new
LM Studio
Jan

vLLM

How to use miceworks/Mark-Engineer-302M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "miceworks/Mark-Engineer-302M"
# 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-302M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/miceworks/Mark-Engineer-302M:IQ4_NL

Ollama
How to use miceworks/Mark-Engineer-302M with Ollama:
```
ollama run hf.co/miceworks/Mark-Engineer-302M:IQ4_NL
```
Unsloth Desktop
Docker Model Runner
How to use miceworks/Mark-Engineer-302M with Docker Model Runner:
```
docker model run hf.co/miceworks/Mark-Engineer-302M:IQ4_NL
```

Lemonade

How to use miceworks/Mark-Engineer-302M with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull miceworks/Mark-Engineer-302M:IQ4_NL

Run and chat with the model

lemonade run user.Mark-Engineer-302M-IQ4_NL

List all available models

lemonade list

Atomic Chat

Mark Engineer 300M (302M)

Mark Engineer 300M is an experimental micro-scale model (302M physical parameters) designed as a testbed for running Multi-Head Latent Attention (MLA) and DeepSeekMoE routing on severely constrained edge hardware and micro-nodes.

License: GNU Affero General Public License v3.0 (AGPL-3.0)
Parameters: 302,019,848 physical | ~110,000,000 active FLOPs per token
Architecture: 12 layers, hidden dimension 1,024, MLA ($c_{KV}=256$), 16 routed + 1 shared expert (top-2 active)
Target Footprint: ~350 MB VRAM, 280+ tokens/second on consumer hardware

Technical Scope & Important Limitations

1. Non-Conversational Model

Mark Engineer 300M does not have the capacity for natural, multi-turn conversational dialogue or explanatory prose. Its parameter budget was allocated toward structural code patterns and tensor graph verification. In open-ended dialogue, the model will produce disjointed output, repetitive tokens, or grammatical breakdowns.

2. High Hallucination Rate in Open-Ended Generation

Due to the strict 302M parameter limit, complex architectural design, multi-file reasoning, and general programming tasks exceed the model's expressive capacity. On standard HumanEval (Python), the model scores under 15%.

3. Intended Use Cases

Edge Micro-Nodes: Experimental deployment on devices with under 500 MB of total RAM/VRAM.
Deterministic Micro-Kernels: Verifying narrow C macros, packed struct alignments, and fixed bitwise manipulation templates.
Architectural Profiling: Serving as a low-cost testbed for benchmarking MLA and MoE runtime kernels on CPU and low-power hardware.

If your use case requires full systems engineering dialogue, low-level kernel synthesis, or general coding assistance, use Mark Engineer 1.5B.

Evaluation Results on Narrow Synthetic Suites

Evaluation Suite	Result / Pass Rate	Notes
C Packed Struct Alignment (4-byte/8-byte)	82.0% (41/50)	Follows rigid alignment directives without padding errors.
Bitwise Endianness Swap Templates (`bswap32`)	86.0% (43/50)	Correctly outputs bit-shift masks for endian swaps.
Fixed Ringbuffer Index Modulo Arithmetic	78.0% (39/50)	Correctly handles index wrap-around logic.
Standard HumanEval (Python Pass@1)	12.4%	Fails complex multi-step reasoning and algorithmic tasks.
Open Dialogue / Conversational Coherence	Unsatisfactory	Fails natural multi-turn conversational evaluation.

Hardware Profile

Metric	Measurement (NVIDIA RTX 2060 Super 8GB)
Weights Memory (IQ4_NL)	225 MB
Runtime VRAM Footprint	~350 MB
Throughput	284 tokens/second

Quickstart

Ollama

ollama run mark-engineer-302m:latest "/* C Packed Struct */ struct __attribute__((packed)) eth_hdr {"

Hugging Face Hub (GGUF)

huggingface-cli download miceworks/Mark-Engineer-302M mark_engineer_302m_iq4_nl.gguf --local-dir ./weights

Downloads last month: 16

GGUF

Model size

0.1B params

Architecture

llama

Hardware compatibility

4-bit