yuseiito/Qwen3-Swallow-30B-A3B-RL-v0.2-GGUF

Same weights, converted vs tokyotech-llm/Qwen3-Swallow-30B-A3B-RL-v0.2. Same weights stored in another dtype (BF16 → BF16/F32), plus 144 new tensors.

Tensors changed: Embeddings 0/1, lm_head 0/1, Norms 0/193, MLP 0/48, Attention 0/192

On the Hub · Downloads on Model Pulse