Qwen3-14B-MLX-8bit

Revision 86a7e1c12ba5c03be148a3e36db45dbca03d2b65

Open on Hugging Face Plan a deployment

14.8BTOTAL PARAMETERS

—CHECKPOINT BYTES

— / —EXPERTS / PER TOKEN

67KDOWNLOADS

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
`U32`	14,767,882,240	4	59.1 GB	—
`BF16`	424,960	2	849920 B	—

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: qwen3config.model_type
Model classes: Qwen3ForCausalLMconfig.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: 14,768,307,200safetensors.total
Checkpoint bytes: UndeterminedPer-dtype tensor bytes (59072378880) exceed the repository's stored bytes (15703262696), so the dtype map cannot be read literally for this checkpoint.
Ships below 16-bit: UndeterminedPrecision cannot be characterised from an inconsistent dtype map.
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-2.0cardData.license
Base model: Qwen/Qwen3-14BcardData.base_model
Library: mlxlibrary_name
Files in repository: 11siblings
Last modified: 2025-04-28lastModified

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/lmstudio-community/Qwen3-14B-MLX-8bit 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