oamazonasgabriel/ qwen3.6-35b-a3b

830 1 month ago

A memory-efficient model configuration of Qwen3.6-35B-A3B using an upstream imatrix-calibrated IQ4_XS quantization and q4_0 KV cache. Designed for 24 GB VRAM

tools thinking

1 model

qwen3.6-35b-a3b:q4-24gbGPU
73ab4af547f8 • 19GB • 256K context window •
Text input • 1 month ago