StargazerLabs/Qwen3.8-32B-Jumbo

Partial fine-tune vs Qwen/Qwen3.8-27B. Partial change: 77% of the weights changed (attention, mlp, norms), in 64 of 64 layers.

Tensors changed: Norms 199/208, Attention 325/400, MLP 156/192, Embeddings 0/1

4 derivatives checked

• GeoMaciolek/Qwen3.8-32B-Jumbo-Q4_K_S-GGUF: Quantization
• StargazerLabs/Qwen3.8-32B-Jumbo-8bit: Quantization
• StargazerLabs/Qwen3.8-32B-Jumbo-4bit: Quantization
• StargazerLabs/Qwen3.8-32B-Jumbo-3bit: Quantization

On the Hub · Downloads on Model Pulse