$ ls ~/models/

Models

Fine-tunes I train on a single DGX Spark and publish as GGUF on Hugging Face, with a write-up on X for each release.

Javi0.2-4B (alpha)

A 4B agent model fine-tuned from Qwen3.5-4B to look things up instead of guessing, say so when it can't verify, and reason from first principles. Trained on one DGX Spark.

GGUF · Q8_0 / Q4_K_M · base Qwen3.5-4B

AgentFine-tuneDGX Spark

Hugging Face write-up on X

Qwen3-4B Pirate

Qwen3-4B-Instruct-2507 fine-tuned to answer everything in heavy pirate dialect, no system prompt needed. LoRA trained in 7m20s on one DGX Spark with Unsloth; 74.5 tok/s at Q4_K_M on Spark.

GGUF · Q4_K_M · base Qwen3-4B-Instruct-2507

LoRAUnslothDGX Spark

Hugging Face write-up on X