ryanfortin/community-blend-qwen3-8b

Full fine-tune vs AXCXEPT/Qwen3-EZO-8B-beta. Fine-tune: 100% of the weights changed, across 36 of 36 layers.

Tensors changed: Embeddings 1/1, Norms 136/145, MLP 108/108, Attention 144/144, lm_head 1/1

2 derivatives checked

• mradermacher/community-blend-qwen3-8b-i1-GGUF: Quantization
• mradermacher/community-blend-qwen3-8b-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse