Views
No views yet
| Source | mach-kernel/ecu-pilot-fp16 |
| Method | Q8_0 via llama.cpp |
| Size | ~35 GB |
| Architecture | Mixture of Experts (35B total, 3B active per token) |
1echo 'FROM ./ecu-pilot-q8_0.gguf
2PARAMETER temperature 0.2
3PARAMETER num_ctx 8192
4PARAMETER stop <|im_end|>' > Modelfile
5
6ollama create ecu-pilot -f Modelfile
7ollama run ecu-pilotllama-cli -m ecu-pilot-q8_0.gguf -ngl 99 -cnv| Format | Repository | Size |
|---|---|---|
| FP16 | mach-kernel/ecu-pilot-fp16 | ~67 GB |
| GGUF Q4_K_M | mach-kernel/ecu-pilot-q4km | ~20 GB |
| GGUF Q8_0 (this repo) | mach-kernel/ecu-pilot-q8_0 | ~35 GB |
| LoRA adapter | mach-kernel/ecu-pilot-fp16-lora | ~4 GB |