Downtown-Case/

GLM-4.5-Base-128GB-RAM-IQ2_KL-GGUF

llm_load_tensors:        CPU buffer size = 114156.88 MiB
llm_load_tensors:  CUDA_Host buffer size =   416.25 MiB
llm_load_tensors:      CUDA0 buffer size = 10584.35 MiB

# Attention
blk\..*\.attn_q.*=iq5_ks
blk\..*\.attn_k.*=iq6_k
blk\..*\.attn_v.*=iq6_k
blk\..*\.attn_output.*=iq5_ks

# First 3 Dense Layers [0-2]
blk\..*\.ffn_down\.weight=iq5_ks
blk\..*\.ffn_(gate|up)\.weight=iq5_ks

# Shared Expert Layers [3-92]
blk\..*\.ffn_down_shexp\.weight=iq5_ks
blk\..*\.ffn_(gate|up)_shexp\.weight=iq5_ks

# Routed Experts Layers [3-19]
blk\.[3-9]\.ffn_down_exps\.weight=iq3_ks
blk\.[3-9]\.ffn_(gate|up)_exps\.weight=iq3_ks
blk\.[1-1][0-9]\.ffn_down_exps\.weight=iq3_ks
blk\.[1-1][0-9]\.ffn_(gate|up)_exps\.weight=iq3_ks

# Routed Experts Layers [81-92]
blk\.[8-8][1-9]\.ffn_down_exps\.weight=iq3_ks
blk\.[8-8][1-9]\.ffn_(gate|up)_exps\.weight=iq3_ks
blk\.[9-9][0-2]\.ffn_down_exps\.weight=iq3_ks
blk\.[9-9][0-2]\.ffn_(gate|up)_exps\.weight=iq3_ks

# Routed Experts Layers [20-80]
blk\..*\.ffn_down_exps\.weight=iq2_kl
blk\..*\.ffn_(gate|up)_exps\.weight=iq2_kl

# NextN MTP Layer [92]
blk\..*\.nextn\.embed_tokens\.weight=iq5_ks
blk\..*\.nextn\.shared_head_head\.weight=iq5_ks
blk\..*\.nextn\.eh_proj\.weight=q8_0

# Non-Repeating Layers
token_embd\.weight=iq4_k
output\.weight=iq6_k