DavidAU/Qwen3-Coder-42B-A3B-Instruct-TOTAL-RECALL-MASTER-CODER-M-1million-ctx

Partial fine-tune vs Qwen/Qwen3-Coder-30B-A3B-Instruct. Partial change: 9% of the weights changed (attention, lm_head, mlp, norms), in 1 of 48 layers.

Tensors changed: Embeddings 0/1, Norms 5/193, MLP 36/1763, Attention 4/192, lm_head 1/1

2 derivatives checked

• mradermacher/Qwen3-Coder-42B-A3B-Instruct-TOTAL-RECALL-MASTER-CODER-M-1million-ctx-i1-GGUF: Quantization
• mradermacher/Qwen3-Coder-42B-A3B-Instruct-TOTAL-RECALL-MASTER-CODER-M-1million-ctx-GGUF: Quantization

On the Hub · Downloads on Model Pulse