exnivo/Qwen3.8-20B-Minitron

Partial fine-tune vs Qwen/Qwen3.8-27B. Partial change: 85% of the weights changed (attention, mlp, norms), in 44 of 44 layers.

Tensors changed: Norms 130/254, Attention 299/416, MLP 132/244, Embeddings 0/4, lm_head 0/1

3 derivatives checked

• mradermacher/Qwen3.8-20B-Minitron-i1-GGUF: Quantization
• mradermacher/Qwen3.8-20B-Minitron-GGUF: Quantization
• Miltos22/Qwen3.8-20B-Minitron-Q3_K_S-GGUF: Quantization

On the Hub · Downloads on Model Pulse