Kimi K3 0.40B is an open-source language model by inference-optimization. Features: 0.40b LLM, VRAM: 1.6GB, License: mit, LLM Explorer Score: 0.47.
Base model:finetune:moonshotai... Base model:moonshotai/kimi-k3 Custom code Feature-extraction Kimi k3 Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/inference-optimization/Kimi-K3-0.40B
Kimi K3 0.40B Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
Kimi K3 0.40B Parameters and Internals
| LLM Name | Kimi K3 0.40B |
| Repository 🤗 | https://huggingface.co/inference-optimization/Kimi-K3-0.40B |
| Base Model(s) | |
| Model Size | 0.40b |
| Required VRAM | 1.6 GB |
| Updated | 2026-07-30 |
| Maintainer | inference-optimization |
| Model Type | kimi_k3 |
| Model Files | |
| Model Architecture | KimiK3ForConditionalGeneration |
| License | mit |
| Transformers Version | 5.15.0.dev0 |
| Tokenizer Class | TikTokenTokenizer |
| Padding Token | [PAD] |
Best Alternatives to Kimi K3 0.40B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...mi K3 0.40B Kazakh CPT Step200 | 0K / 0.8 GB | 71 | 1 |
Rank the Kimi K3 0.40B Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 55501 in total.
Original data from HuggingFace, Arena and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a