CATALOGUE RECORD / HUB-DERIVED
Qwen
Qwen3-30B-A3B
Revision ad44e777bcd18fa416d9da3bd8f70d33ebb85d39
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 | 30,532,122,624 | 2 | 61.1 GB | 100.0% |
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
- qwen3_moe
config.model_type - Model classes
- Qwen3MoeForCausalLM
config.architectures - Routed experts
- 128
config.num_experts - Experts per token
- 8
config.num_experts_per_tok - Shared experts
- UndeterminedThe published config declares no always-on shared experts.
- Routing sparsity
- 16.0× (1 of every 16.0 experts)
config.num_experts / config.num_experts_per_tok - Total parameters
- 30,532,122,624
safetensors.total - Checkpoint bytes
- 61,064,245,248 (61.1 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
- apache-2.0
cardData.license - Base model
- Qwen/Qwen3-30B-A3B-Base
cardData.base_model - Library
- transformers
library_name - Files in repository
- 26
siblings - Last modified
- 2025-07-26
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.