jakeatx/slimder-qwen38-ream288-depth32-agentic-ngram50-compact
Same weights, repacked vs jakeatx/slimder-qwen38-ream288-depth32-agentic. Same weights in different files (re-saved, re-sharded or new metadata), plus 2 new tensors.
Tensors changed: lm_head 0/1, Embeddings 0/4, Norms 0/124, other 0/5, Attention 0/328, MLP 0/320
3 derivatives checked
- jakeatx/Qwen3.8-Perian-GGUF: Not comparable yet
- jakeatx/slimder-qwen38-ream288-depth32-agentic-ngram50-mixed-nvfp4-v2: Quantization
- jakeatx/slimder-qwen38-ream288-depth32-agentic-ngram50-compact-nvfp4: Quantization