Downloads · 30 days
179
22% of all-time downloads
wrldsuksgo2mars/GLM-5.3-EXL3-K4-v1
GLM-5.3-EXL3-K4-v1 is a text generation model from wrldsuksgo2mars. Use it when you need the model to write or continue text. The card lists the license as other.
This is a calibrated 4-bit EXL3 quantization of zai-org/GLM-5.3.
Downloads · 30 days
179
22% of all-time downloads
All-time downloads
805
Public
Parameters
210B
394 GB on disk
Likes
2
Public
Click a slice to open those files.
.safetensors394 GB · 100%
How the weights are stored.
I16181B · 86%
From the Hugging Face model README
This is a calibrated 4-bit EXL3 quantization of zai-org/GLM-5.3.
The routed expert gate_proj, up_proj, and down_proj tensors in base-model
layers 3 through 77 use the EXL3 K4 representation. Other tensors, including
the native MTP overlay, retain their source representation. The repository
contains 46 safetensors shards and the complete quantization metadata in
quantize_config.json.
This is an EXL3 checkpoint, not a drop-in GPTQ or standard Transformers checkpoint. Use a serving runtime that supports GLM-5.3 MoE/DSA and this EXL3 tensor layout. Check runtime compatibility before downloading the full model.
The best observed tool-eval-bench run scored 91/100 (125/138 raw points)
with fixed DFlash2 draft width 5. This is a single local evaluation result and
is not an official upstream GLM-5.3 benchmark.
This derivative checkpoint is distributed under the GLM-5.3 model license.
Review and comply with the license terms of the original zai-org/GLM-5.3
model before use.