alamios/Qwemma-3-0.5B

Same weights, repacked vs Qwen/Qwen2.5-0.5B. Same weights in different files (re-saved, re-sharded or new metadata), plus 1 new tensors.

Tensors changed: Norms 0/49, MLP 0/72, Attention 0/168

2 derivatives checked

• jmfirth/Qwemma-3-0.5B-mlx-8Bit: Quantization
• mradermacher/Qwemma-3-0.5B-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse