schema_version: 1
kind: model
extends: glm
description: GLM-5.3 Flash with NVFP4 routed experts and an MXFP8 MTP expert layer
weight_bytes: 198042331512
served_model_name: zai-org/GLM-5.3-Flash
expected_architectures:
  - Glm5NextForConditionalGeneration
quantization: modelopt_mixed
block_size: 256
disable_flashinfer_autotune: true
default_speculator: mtp
mtp_tokens: 5
dflash2_tokens: 7
mtp_attention_backend: B12X
mm_encoder_tp_mode: data
mm_processor_cache_gb: 0
launch:
  local:
    default_tp_size: 4
    defaults:
      environment:
        INSTANTTENSOR_BUFFER_SIZE: "67108864"
        INSTANTTENSOR_CHUNK_SIZE: "8388608"
  spark_rdma:
    default_tp_size: all
    defaults:
      environment:
        INSTANTTENSOR_BUFFER_SIZE: "67108864"
        INSTANTTENSOR_CHUNK_SIZE: "8388608"
mtp_moe_quantization: mxfp8
dflash2_model: local-inference-lab/GLM-5.3-Flash-DFlash2-MXFP8