t-tech/T-Search

Full fine-tune vs Qwen/Qwen3.6-35B-A3B. Fine-tune: 95% of the weights changed, across 40 of 40 layers.

Tensors changed: Embeddings 0/5, Attention 236/392, MLP 280/399, Norms 94/247, lm_head 1/1, other 0/1

5 derivatives checked

• IsValorum/T-Search-APEX-I-MiniPlus-V2.1-GGUF: Quantization
• bartowski/t-tech_T-Search-GGUF: Same weights, converted
• t-tech/T-Search-GGUF: Quantization
• t-tech/T-Search-FP8: Quantization
• t-tech/T-Search-NVFP4: Quantization

On the Hub · Downloads on Model Pulse