IsValorum/Ornith-1.5-35B-A3B-APEX-I-MiniPlus-V2.1-GGUF
Show direct Ko-fi URL
Number navigation and refine optional support
Complete navigation index and remove duplicate support block
Move navigation to top and clarify optional support
Add optional Ko-fi support link
Connect model tree directly to official BF16 model: ornith-ai/Ornith-1.5-35B-A3B
Update YAML metadata tags: Qwen3.6 base & finetune lineage
Add reciprocal cross-links between MiniPlus and NanoPlus editions
Refine quality tier architectural breakdown
Document Q5_K_M / Q5_K_L quality tier breakdown
Correct fidelity tiers against measured delta perplexity
Add compact model-specific V2.1 comparison table
Correct base-model metadata and source links
Add Qwen3.6 Abliterated V2.1 to lineup links
Replace generic Q5-Q6 redundancy with exact verified Q6_K quality tier
Identify MiniPlus V2.1 edition in lineup links
Clarify established 35B MoE lineup and cross-links
Document measured BF16 baselines and delta perplexity
Apply V2.1 README standard to Ornith 1.5
Add system RAM inference guidance
Add comprehensive model card, empirical benchmarks, and collection cross-links
Add companion mmproj-Q8_0.gguf multimodal vision projector
Add Ornith-1.5-35B-A3B APEX-I-MiniPlus-V2.1 GGUF (3.40 BPW surgical quantization)
initial commit