miceworks/Mark-Engineer-302M

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