CATALOGUE RECORD / HUB-DERIVED
zai-org
GLM-4.7-Flash
Revision 7dd20894a642a0aa287e9827cb1a1f7f91386b67
TENSOR ACCOUNTING
Where the bytes are.
Summed from the safetensors index, one row per dtype. A parameter count alone cannot produce this figure, because a checkpoint may mix widths.
| Dtype | Parameters | Bytes each | Bytes | Share |
|---|---|---|---|---|
BF16 | 31,221,485,568 | 2 | 62.4 GB | 100.0% |
F32 | 3,008 | 4 | 12032 B | 0.0% |
EVERY FIELD, WITH ITS ORIGIN
Sourced or undetermined. Never assumed.
Each value below names the exact API field it was computed from. Where the Hub does not establish a value, the reason is shown instead of a plausible default.
- Architecture
- glm4_moe_lite
config.model_type - Model classes
- Glm4MoeLiteForCausalLM
config.architectures - Routed experts
- UndeterminedThe published config exposes no routed-expert count. The Hub's config summary omits fields some architectures place only in the full config.json.
- Experts per token
- 4
config.num_experts_per_tok - Shared experts
- UndeterminedThe published config declares no always-on shared experts.
- Routing sparsity
- UndeterminedRouting sparsity requires both a routed-expert and a per-token expert count.
- Total parameters
- 31,221,488,576
safetensors.total - Checkpoint bytes
- 62,442,983,168 (62.4 GB)
safetensors.parameters - Ships below 16-bit
- No
safetensors.parameters - Quantisation method
- UndeterminedThe repository declares no quantization method, which normally means unquantized weights.
- Trained context
- UndeterminedThe config summary omits max_position_embeddings. Trained context is a model-card claim, not a derivable fact.
- Declared licence
- mit
cardData.license - Base model
- UndeterminedThe repository declares no base model.
- Library
- transformers
library_name - Files in repository
- 58
siblings - Last modified
- 2026-01-29
lastModified
LICENCE POSTURE
Permissive
The repository declares a licence that is generally read as permitting commercial use. Read the licence file in the repository before relying on that.
This is a reading of a metadata field, not legal advice, and it does not account for the licences of upstream models or training data.
WEIGHT RESIDENCY FLOOR
The count below which it cannot fit.
Ceiling of checkpoint bytes over advertised accelerator memory. This is a lower bound on accelerator count for weights alone — KV cache, activations and runtime overhead all sit on top, so a real deployment needs more.