RabotniKuma/Fast-Math-Qwen3-14B

Partial fine-tune vs Qwen/Qwen3-14B. Partial change: 89% of the weights changed (attention, mlp, norms), in 40 of 40 layers.

Tensors changed: Embeddings 0/1, Norms 104/161, MLP 120/120, Attention 160/160, lm_head 0/1

2 derivatives checked

• mradermacher/Fast-Math-Qwen3-14B-GGUF: Quantization
• mradermacher/Fast-Math-Qwen3-14B-i1-GGUF: Quantization

On the Hub · Downloads on Model Pulse