You can deploy this model and start earning money today!

androidlover5842/
qwen3.6-35b-a3b-q6k-droplet

Name: qwen3.6-35b-a3b-q6k-droplet
Availability: InStock

Views

No views yet

Qwen3.6-35B-A3B - pure Q6_K

Pure Q6_K quantization of Qwen3.6-35B-A3B (all tensors q6_K, no imatrix, llama.cpp). For engines requiring uniform q6_k weight tensors.

Source: Qwen/Qwen3.6-35B-A3B (bf16)
Converted with llama.cpp convert_hf_to_gguf.py --outtype bf16 --no-nextn (NextN/MTP draft tensors excluded)
Quantized with llama-quantize ... Q6_K (no imatrix, no mixed types)
arch qwen35moe, 40 blocks, 256 experts, 733 tensors, 432 x q6_K + 301 x f32