qwen3-davesoma-v2-gguf

GGUF export for local inference (llama.cpp / Ollama workflows).

• Quantization: Q4_K_M
• File: qwen3_8b_davesoma_v2.Q4_K_M.gguf

Suggested use

• Fast local drafting in the davesoma style
• Opinion framing and concise technical responses

Notes

• This is a quantized inference artifact. For reproducible training workflows, use the LoRA repo.
• Pair with retrieval for factual tasks.

Related repos

• LoRA adapter: davesoma/qwen3-davesoma-v2-lora
• Blog context: https://dscompounding.com/