GLM-5.2-REAM-GGUF

What this is

• Base: coder3101/GLM-5.2-REAM which was removed after I downloaded it, which is based on zai-org/GLM-5.2 (glm_moe_dsa, ~753B MoE).
• Runs as full MLA attention (the DSA lightning-indexer is not used at inference — same simplification as the upstream conversion).
• Quantized using llama.cpp.

Recommended serving — recover most of the loop gap for free

• Anti-loop (recommended):
  • min_p=0.05, repetition_penalty=1.05
  • min_p=0.05, repetition_penalty=1.10
  Start at 1.05; go to 1.10 if you see loops — a higher repetition penalty trades a little risk of over-penalizing legitimate repetition (e.g. in code) for near-zero looping.