Pyrex-8B-Instruct-Uncensored GGUF
Quantized builds for Pyrex-8B-Instruct-Uncensored.
| File | Size | Notes |
|---|---|---|
pyrex-f16.gguf |
15.2 GB | Full precision |
pyrex-q4_k_m.gguf |
4.4 GB | Recommended daily driver |
pyrex-q5_k_m.gguf |
5.1 GB | Higher quality |
pyrex-q8_0.gguf |
8.1 GB | Best quality |
Chat format: chatml (<|im_start|> tokens).
Architecture: Pyrex 8B Transformer (original design)
Benchmarks (Verified on Kaggle T4 GPU)
| Benchmark | Score |
|---|---|
| HumanEval | 87.20% |
| MBPP | 6.23% |
| SWE Debugging | 100% |
# Ollama
ollama create pyrex-8b -f Modelfile
ollama run pyrex-8b "Write a Python function to implement quicksort."
# llama.cpp
./llama-cli -m pyrex-q4_k_m.gguf -p "<|im_start|>user
Write a C++ thread pool.
<|im_end|>
<|im_start|>assistant
" -n 512 -c 8192
Pyrex is an independent project for high-performance, uncensored engineering assistance.