Qwen3-VL-30B-A3B-Instruct-AWQ

Revision a5ea10732e2c9330957864ece3ec66d806a4b00d

Open on Hugging Face Plan a deployment

31.1BTOTAL PARAMETERS

—CHECKPOINT BYTES

— / —EXPERTS / PER TOKEN

1.5MDOWNLOADS

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
`I32`	29,896,998,912	4	119.6 GB	—
`F16`	1,173,755,120	2	2.3 GB	—

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_vl_moeconfig.model_type
Model classes: Qwen3VLMoeForConditionalGenerationconfig.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: UndeterminedThe published config exposes no per-token expert count.
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: 31,070,754,032safetensors.total
Checkpoint bytes: UndeterminedThis checkpoint packs 4-bit weights into wider integer containers, so element count multiplied by container width is not the checkpoint size. Use repository storage, which is measured on disk.
Ships below 16-bit: Yesconfig.quantization_config.bits
Quantisation method: awqconfig.quantization_config.quant_method
Trained context: UndeterminedThe config summary omits max_position_embeddings. Trained context is a model-card claim, not a derivable fact.
Declared licence: apache-2.0cardData.license
Base model: Qwen/Qwen3-VL-30B-A3B-InstructcardData.base_model
Library: transformerslibrary_name
Files in repository: 19siblings
Last modified: 2025-10-08lastModified

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.

PROVENANCE

Derived from https://huggingface.co/api/models/QuantTrio/Qwen3-VL-30B-A3B-Instruct-AWQ in the snapshot generated 2026-09-05. Evidence class hub_derived: computed mechanically from publisher metadata, never measured by this project.

Back to catalogue How evidence is classified