maldv/QReasoner2.5-32B-Instruct

Full fine-tune vs OpenPipe/Deductive-Reasoning-Qwen-32B. Fine-tune: 98% of the weights changed, across 64 of 64 layers.

Tensors changed: Embeddings 0/1, Norms 129/129, MLP 192/192, Attention 448/448, lm_head 1/1

3 derivatives checked

• mradermacher/QReasoner2.5-32B-Instruct-i1-GGUF: Quantization
• featherless-ai-quants/maldv-QReasoner2.5-32B-Instruct-GGUF: Quantization
• mradermacher/QReasoner2.5-32B-Instruct-GGUF: Quantization

On the Hub · Downloads on Model Pulse