## Quant mix recipe created using Thireus' GGUF Tool Suite - https://gguf.thireus.com/

## Model head & embeddings — qbits: 32 6 5 
^output_norm\.weight$=f32
^token_embd\.weight$=iq5_ks
^output\.weight$=iq6_k

## Multi-headed attention parameters — qbits: 32 8 5 
^blk\.([0-9]|[1-8][0-9]|9[0-2])\.attn_norm\.weight$=f32
^blk\.([0-9]|[1-8][0-9]|9[0-2])\.attn_k_norm\.weight$=f32
^blk\.([0-9]|[1-8][0-9]|9[0-2])\.attn_v\.weight$=q8_0
^blk\.([0-9]|[1-8][0-9]|9[0-2])\.attn_v\.bias$=f32
^blk\.([0-9]|[1-8][0-9]|9[0-2])\.attn_q\.bias$=f32
^blk\.([0-9]|[1-8][0-9]|9[0-2])\.attn_q_norm\.weight$=f32
^blk\.([0-9]|[1-8][0-9]|9[0-2])\.attn_k\.bias$=f32
^blk\.([0-9]|[1-8][0-9]|9[0-2])\.attn_k\.weight$=q8_0
^blk\.([0-9]|[1-8][0-9]|9[0-2])\.attn_q\.weight$=iq5_ks
^blk\.([0-9]|[1-8][0-9]|9[0-2])\.attn_output\.weight$=iq5_ks

## Dense Feed-Forward Network weights — qbits: 8 
^blk\.[0-2]\.ffn_gate\.weight$=q8_0
^blk\.[0-2]\.ffn_down\.weight$=q8_0
^blk\.[0-2]\.ffn_up\.weight$=q8_0

## NextN tensors — qbits: 32 5 
^blk\.92\.nextn\.enorm\.weight$=f32
^blk\.92\.nextn\.eh_proj\.weight$=iq5_ks
^blk\.92\.nextn\.embed_tokens\.weight$=iq5_ks
^blk\.92\.nextn\.shared_head_norm\.weight$=f32
^blk\.92\.nextn\.shared_head_head\.weight$=iq5_ks
^blk\.92\.nextn\.hnorm\.weight$=f32

## MoE Gating & Routing — qbits: 32 
^blk\.([3-9]|[1-8][0-9]|9[0-2])\.ffn_gate_inp\.weight$=f32
^blk\.([3-9]|[1-8][0-9]|9[0-2])\.exp_probs_b\.bias$=f32

## Misc / Other tensors — qbits: 32 
^blk\.([0-9]|[1-8][0-9]|9[0-2])\.post_attention_norm\.weight$=f32

## GPU-loaded - MoE Shared Experts Feed-Forward Network - ffn_*_shexp
# ffn_down_shexp — down-projection (shared experts) — qbits: 8 
^blk\.([3-9]|[1-8][0-9]|9[0-2])\.ffn_down_shexp\.weight$=q8_0

# ffn_up_shexp — up-projection (shared experts) — qbits: 8 
^blk\.([3-9]|[1-8][0-9]|9[0-2])\.ffn_up_shexp\.weight$=q8_0

# ffn_gate_shexp — gating network (shared experts) — qbits: 8 
^blk\.([3-9]|[1-8][0-9]|9[0-2])\.ffn_gate_shexp\.weight$=q8_0

## CPU-friendly - MoE Per-expert Feed-Forward Network - ffn_*_exps
# ffn_down_exps — down-projection (per-expert) — qbits: 4 3 2 
^blk\.([3-5]|8|11|14|18|22|25|3[0-1]|35|43|46|5[6-7]|61|92)\.ffn_down_exps\.weight$=iq4_kss
^blk\.(6|13|1[5-6]|19|24|28|37|42|4[4-5]|4[7-9]|5[0-5]|59|60|6[2-6]|68|7[1-6]|78|8[1-2]|86)\.ffn_down_exps\.weight$=iq3_ks
^blk\.(10|12|17|21|23|2[6-7]|29|32|34|36|3[8-9]|40)\.ffn_down_exps\.weight$=iq2_ks
^blk\.(7|9|20|33|41|58|67|69|70|77|79|80|8[3-5]|8[7-9]|9[0-1])\.ffn_down_exps\.weight$=iq2_kl

# ffn_up_exps — up-projection (per-expert) — qbits: 4 3 2 
^blk\.(11|13|1[5-6]|19|20|24|28|34|44|5[6-7]|92)\.ffn_up_exps\.weight$=iq4_kss
^blk\.(14|17|23|3[0-1]|36|4[0-3]|4[6-9]|5[0-5]|5[8-9]|6[0-2]|6[4-5]|6[7-9]|7[0-9]|8[1-2]|85|88|91)\.ffn_up_exps\.weight$=iq3_ks
^blk\.([3-5]|8|12|2[1-2]|3[8-9]|45|63|66|80|8[3-4]|8[6-7]|89|90)\.ffn_up_exps\.weight$=iq2_kl
^blk\.([6-7]|9|10|18|2[5-7]|29|3[2-3]|35|37)\.ffn_up_exps\.weight$=iq2_ks

# ffn_gate_exps — gating network (per-expert) — qbits: 4 3 2 
^blk\.(1[0-2]|17|19|2[0-3]|28|3[0-1]|92)\.ffn_gate_exps\.weight$=iq4_kss
^blk\.(1[3-6]|24|26|41|4[3-8]|5[0-9]|6[0-1]|6[3-5]|6[7-9]|7[0-6]|78|[8-9][0-1]|87)\.ffn_gate_exps\.weight$=iq3_ks
^blk\.([3-4]|[6-7]|33|39|42|49|62|66|77|79|8[2-6]|8[8-9])\.ffn_gate_exps\.weight$=iq2_kl
^blk\.(5|[8-9]|18|25|27|29|32|3[4-8]|40)\.ffn_gate_exps\.weight$=iq2_ks

## Summary of tensor sizes per class
# GPU Total: 12.13 GiB (100.0%) | 12.13 GiB max, if all were q8_0 | 12.13 GiB min, if all were q8_0
# CPU Total: 122.03 GiB (76.7%) | 159.18 GiB max, if all were iq4_kss | 88.29 GiB min, if all were iq2_ks
# GPU+CPU Total: 134.17 GiB (88.3%)

## Summary of tensor counts and bpw per qtype
#
# GPU-loaded quants:
# QTYPE		Count	BPW	Assigned GiB	% Assigned	Max GiB (all)
# +f32       	835	32    	  0.28 GiB	-		-
# +q8_0      	186	8.5   	  0.96 GiB	-		-
# q8_0      	279	8.5   	  2.66 GiB	100.0%		2.66
# +iq6_k     	1  	6.625 	  0.60 GiB	-		-
# +iq5_ks    	187	5.25  	  7.63 GiB	-		-
#
# CPU-friendly quants:
# QTYPE		Count	BPW	Assigned GiB	% Assigned	Max GiB (all)
# +iq5_ks    	3  	5.25  	  0.98 GiB	-		-
# +iq4_kss   	3  	4     	  1.76 GiB	-		-
# iq4_kss   	41 	4     	 24.02 GiB	15.4%		156.45
# iq3_ks    	127	3.1875	 59.30 GiB	47.6%		124.67
# iq2_kl    	58 	2.6875	 22.83 GiB	21.7%		105.11
# iq2_ks    	41 	2.1875	 13.14 GiB	15.4%		85.56
#
# -Average BPW: 3.2162
#
# -Notes:
# - '+' means user-defined pre-assigned tensors, or tensor missing from csv data or f32 tensors
# - Recipe produced on the 2025-11-28 06:08:52 WIB+0700 using Thireus' GGUF tools (https://gguf.thireus.com/)
# - Script SHA-256: 569b7f6a3239c9173d71ca1fadf34222607d72a2cfed2c284b42633e95b4a627
# - Calibration dataset 'models/GLM-4.5/ppl_results.csv' SHA-256: eee3f314cf1ecaa746932341b2189f8a7718e62489bbd250f957c4aec82c0015
# - tensors.bf16.map SHA-256: 4e8b7b435f6257174a7adfc90290ac92c36758fef201ba0f5358338eea7606b8
# - tensors.bf16.map model name: GLM-4.5-THIREUS-BF16-SPECIAL_TENSOR-01762-of-01762
# - tensors.q8_0.map SHA-256: 2814e1547cf288d327264135ed3f83e612b879826640283037d45f95a22ebfe2
# - tensors.q8_0.map model name: GLM-4.5-THIREUS-Q8_0-SPECIAL_TENSOR-01762-of-01762
# - tensors.iq6_k.map SHA-256: 8ef4d5c379126fc13dfb46bbc8c10308d2c8e78602c0b3f6cea197d963fc80f1
# - tensors.iq6_k.map model name: GLM-4.5-THIREUS-IQ6_K-SPECIAL_TENSOR-01762-of-01762
# - tensors.iq5_ks.map SHA-256: 9af5c1536eebc84dc6c71d855517c9acd534fbeefc3067aef26def0c104c7e64
# - tensors.iq5_ks.map model name: GLM-4.5-THIREUS-IQ5_KS-SPECIAL_TENSOR-01762-of-01762
# - tensors.iq4_kss.map SHA-256: 78644e76c921c329b6cf32d1c8711766170edea7e8960fcd3e9eb6d94601bc4b
# - tensors.iq4_kss.map model name: GLM-4.5-THIREUS-IQ4_KSS-SPECIAL_TENSOR-01762-of-01762
# - tensors.iq3_ks.map SHA-256: 4a33c7b3901cadf1a4e6130aeaed8806168249a0d386219db4ffec31188cb6af
# - tensors.iq3_ks.map model name: GLM-4.5-THIREUS-IQ3_KS-SPECIAL_TENSOR-01762-of-01762
# - tensors.iq2_kl.map SHA-256: ad6ca540847d2e75cb537169f77e91d8453b70613b3171fed20bc374f202d58a
# - tensors.iq2_kl.map model name: GLM-4.5-THIREUS-IQ2_KL-SPECIAL_TENSOR-01762-of-01762
# - tensors.iq2_ks.map SHA-256: 4ed9fc5a73d854ad30f9f75577a1d826150cb23283a0bb54dba45d6aba6c9de2
# - tensors.iq2_ks.map model name: GLM-4.5-THIREUS-IQ2_KS-SPECIAL_TENSOR-01762-of-01762
# - GPG signatures: DISABLED
# - Command used:
# ./quant_assign.py models/GLM-4.5/ppl_results.csv --tolerance 0.001 --cpu-tensors-max-size 121.9 \
# --gpu-tensors-max-size 12.2 --exponential-factor 1.0 --skip-gpg --cpu-tensors \
# 'blk\.([3-9]|[1-8][0-9]|9[012])\.ffn_down_exps\.weight' 'blk\.([3-9]|[1-8][0-9]|9[012])\.ffn_up_exps\.weight' \
# 'blk\.([3-9]|[1-8][0-9]|9[012])\.ffn_gate_exps\.weight' --gpu-tensors '.*' --cpu-quants iq4_kss iq3_ks iq2_kl \
# iq2_ks --gpu-quants q8_0 --cpu-assign-tensors '^blk\.(92)\.ffn_down_exps\.weight=iq4_kss' \
# '^blk\.(92)\.ffn_up_exps\.weight=iq4_kss' '^blk\.(92)\.ffn_gate_exps\.weight=iq4_kss' \
# '^blk\.92\.nextn\.shared_head_head\.weight=iq5_ks' '^blk\.92\.nextn\.embed_tokens\.weight=iq5_ks' \
# '^blk\.92\.nextn\.eh_proj\.weight=iq5_ks' --gpu-assign-qtype q8_0 --gpu-assign-tensors \
# '^blk\..*\.attn_(q|output)\.weight=iq5_ks' '^token_embd\.weight=iq5_ks' '^output\.weight=iq6_k' --harmonize-tensors \
# '' --harmonization-technique 0

## THE END!