Activity Progression Model 600 — GGUF

Quantized GGUF builds of mjpsm/activity-progression-model-600-qwen3.5-0.8b for MyVillage Activity Progression inference.

Files

• activity-progression-model-600-qwen3.5-0.8b-Q8_0.gguf
  • Recommended first API deployment candidate.
• activity-progression-model-600-qwen3.5-0.8b-Q4_K_M.gguf
  • Smaller candidate; deploy only after regression testing.

Source

The source checkpoint is the already-merged model:

mjpsm/activity-progression-model-600-qwen3.5-0.8b

Deployment

The intended deployment target is a Hugging Face Docker Space using llama.cpp.

Validation requirement

Before production deployment, compare each quantization against the same unseen Progression evaluation set used to select checkpoint 600.