Add model card

README.md

@@ -0,0 +1,24 @@
+---
+base_model: zai-org/GLM-5.3-Flash
+base_model_relation: quantized
+---
+
+# GLM-5.3-Flash-AWQ-W4A16
+
+Quantized version of [zai-org/GLM-5.3-Flash](https://huggingface.co/zai-org/GLM-5.3-Flash).
+
+## What is quantized
+
+Weight-only INT4 (symmetric, group size 128) via AWQ, stored in the compressed-tensors `pack-quantized` format. Calibrated from the official FP8 release (dequantized to BF16 first).
+
+**Quantized (INT4 W4A16):**
+- Routed MoE experts in the 42 MoE decoder layers (layers 3-44): `mlp.experts.{0..287}.{gate_proj, up_proj, down_proj}` (~312B of the 321B parameters)
+
+**Kept in BF16 (not quantized):**
+- Token embedding (`embed_tokens`) and `lm_head`
+- Linear attention / KDA (`self_attn.{q,k,v,o}_proj`, forget gate) and DSA/MLA attention (`q_a/q_b/kv_a/kv_b_proj`, indexer)
+- Hyper-connections (`attn_hc.*`, `ffn_hc.*`)
+- MoE router (`mlp.gate`) and shared experts (`mlp.shared_experts.*`)
+- Dense MLPs of the first 3 layers
+- Vision encoder (`model.visual.*`)
+- NextN/MTP layer (`layers.45.*`, dequantized from the FP8 source to BF16)