Mark Engineer V2 8B is an open-source language model by miceworks. Features: 8b LLM, VRAM: 4.7GB, Context: 8K, Quantized, LLM Explorer Score: 0.31.
| LLM Name | Mark Engineer V2 8B |
| Repository 🤗 | https://huggingface.co/miceworks/Mark-Engineer-V2-8B |
| Model Name | Mark Engineer V2 8B |
| Model Size | 8b |
| Required VRAM | 4.7 GB |
| Updated | 2026-11-01 |
| Maintainer | miceworks |
| Model Type | mark_engineer_v2_8b |
| Model Files | |
| GGUF Quantization | Yes |
| Quantization Type | gguf |
| Model Architecture | MarkEngineerV2ForCausalLM |
| Context Length | 8192 |
| Model Max Length | 8192 |
| Vocabulary Size | 49152 |
| Torch Data Type | bfloat16 |