inference-optimization/Kimi-K3-4.6B-A4.5B-small
feature-extraction model by inference-optimization
Older snapshot: check the original source for current information.
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
This is a small version of moonshotai/Kimi-K3 created for testing and development. It preserves the full architecture characteristics of the base (hybrid KDA linear attention + MLA full attention, latent MoE with shared experts, attention-residual blocks, MoonViT3d vision tower, patchmergerv2 projector) with fewer layers and fewer experts. The following parameters were reduced from the original model (these are the ONLY changes — all other hyperparameters are identical to the base): Layer layout (minimal set covering every distinct attention and MLP type of the base, using combinations that occur in the base): numexpertspertoken (topk) = 16 is unchanged; 18 = topk + 2 so routing is still exercised. numnextnpredictlayers = 0 as in the base (backbone-only checkpoint, no MTP weights). Size note: 4.6B total is the forced minimum for this architecture under the keep-all-hyperparameters constraint: the untied embeddings alone are 2 × 163840 × 7168 ≈ 2.35B params, the single dense-MLP…
Read the full model card ↗ · Preview checked 2026-10-29T05:48:48.876Z
Inside the original model card — Document outline
- Kimi-K3-4.6B-A4.5B-small
- Model Details
- Configuration Changes
- Checkpoint Structure
- Usage
- Creation Process
- Validation Output
- Notes
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Documentation belongs to its respective authors. Reported project/model license: other. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
inference-optimization/Kimi-K3-4.6B-A4.5B-small is a feature-extraction model repository published by inference-optimization on Hugging Face. The source reports the transformers library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- feature-extraction
- Library
- transformers
- Recent downloads (30 days)
- 0
- Cumulative likes
- 0
- Hugging Face trending score
- 0
- Reported safetensors parameters
- 4,609,999,602
- Architecture
- KimiK3ForConditionalGeneration
- License
- other
- Access
- Not gated by Hugging Face
- Created
- 2026-10-20T06:41:10.000Z
- Last modified
- 2026-10-20T06:41:47.000Z
Compatibility and lineage
Language coverage was not reported.
Reported base models: moonshotai/Kimi-K3
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-10-20T06:43:37.702Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.