GLM-5.2-NVFP4-NF3-Hybrid

➡️ Superseded — use madeby561/GLM-5.2-MXFP8-NVFP4-NF3-Hybrid

This was the original hybrid (fp8 non-expert tier). The successor is a drop-in upgrade with the same quality and much more context:

• Same intelligence — GPQA-Diamond 88.38 (parity with the full model), byte-identical NF3 3-bit + NVFP4 4-bit experts.
• 2.44× the KV pool — the non-expert tier is now native MXFP8 (served without a dequant-on-load penalty), freeing VRAM for ~126k → ~267k+ context at DCP4.
• Ready-to-run — a docker-compose.yml + the :v2 image are baked and public.

There's no reason to use this older version.

→ madeby561/GLM-5.2-MXFP8-NVFP4-NF3-Hybrid

---

The full GLM-5.2 — 753B, all 256 experts, no pruning — on 4× 96GB GPUs, via NF3 (our in-house 3-bit expert format) and a custom intra-layer expert-by-expert mixed-precision sm120 kernel: each expert quantized to its own bit-width by saliency, within a single MoE layer. By madeby561.