MARTIN-9B-OMNI

By Zero Point Intelligence Ltd, Dundee, Scotland.

Omni model fine-tuned from Qwen 3.5 9B. Full fine-tune + LoRA, 100K examples, 3 epochs. Supports image-text-to-text generation.

Available Formats

• Full safetensors (FP16) — For fine-tuning or full-precision inference
• Q4_K_M GGUF — Best balance of speed and quality
• Q5_K_M GGUF — Mid-range quantization
• Q6_K GGUF — Higher quality
• Q8_0 GGUF — Near-lossless

Checksums

See checksums.json for SHA256 hashes of all files.