LLM Name | GLM 4 32B 0414 |
Repository ๐ค | https://huggingface.co/THUDM/GLM-4-32B-0414 |
Model Size | 32b |
Required VRAM | 65.7 GB |
Updated | 2025-07-28 |
Maintainer | THUDM |
Model Type | glm4 |
Model Files | |
Supported Languages | zh en |
Model Architecture | Glm4ForCausalLM |
License | mit |
Context Length | 32768 |
Model Max Length | 32768 |
Transformers Version | 4.52.0.dev0 |
Tokenizer Class | PreTrainedTokenizer |
Padding Token | <|endoftext|> |
Vocabulary Size | 151552 |
Torch Data Type | bfloat16 |
Model |
Likes |
Downloads |
VRAM |
---|---|---|---|
GLM 4 32B 0414 GGUF | 47 | 40885 | 7 GB |
GLM 4 32B 0414 4bit DWQ | 4 | 1114 | 18 GB |
GLM 4 32B 0414 8bit | 6 | 1343 | 36 GB |
GLM 4 32B 0414 4bit | 5 | 1100 | 18 GB |
...LM 4 32B 0414 Unsloth Bnb 4bit | 3 | 909 | 20 GB |
GLM 4 32B 0414 Bnb 4bit | 2 | 809 | 19 GB |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
GLM Z1 Rumination 32B 0414 | 128K / 66.4 GB | 1147 | 110 |
GLM Z1 Rumination 32B 0414 | 128K / 66.4 GB | 941 | 112 |
GLM 4 32B 0414 | 32K / 65.7 GB | 117385 | 472 |
GLM Z1 32B 0414 | 32K / 65.7 GB | 2316 | 170 |
GLM Z1 32B 0414 | 32K / 65.7 GB | 2105 | 173 |
GLM 4 32B Base 32K | 32K / 65.4 GB | 785 | 37 |
GLM 4 32B Tulu Instruct | 32K / 65.7 GB | 1352 | 8 |
Austral 32B GLM4 Winton | 32K / 65.7 GB | 98 | 5 |
GLM4 32B Neon V2 | 32K / 65.7 GB | 868 | 18 |
GLM 4 32B Base 0414 | 32K / 65.7 GB | 925 | 28 |
๐ Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! ๐