emergentorder/Qwen3.6-35B-A3B-Mercor-GGUF

This a conversion to GGUF (llama.cpp hf-to-gguf conversion script, with --no-mtp), quantized to Q80, Q6K, Q50 and Q40 by llama-quantize, of:

Qwen3.6-35B-A3B-Mercor

RL post-trained Qwen3.6-35B-A3B on APEX-Agents off-the-shelf datasets.

For more details, see the blog post: **Training frontier knowledge work agents: a 397B RL training guide with SkyRL**