Kimi K3 0.40B Kazakh CPT Step200 is an open-source language model by Eraly-ml. Features: 0.40b LLM, VRAM: 0.8GB, License: mit, LLM Explorer Score: 0.3.
Base model:finetune:inference-... Base model:inference-optimizat... Continued-pretraining Custom code En Experimental Feature-extraction Kazakh Kimi-k3 Kimi k3 Kk Mixture-of-experts Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/Eraly-ml/Kimi-K3-0.40B-Kazakh-CPT-step200
Kimi K3 0.40B Kazakh CPT Step200 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 Kazakh CPT Step200 Parameters and Internals
| LLM Name | Kimi K3 0.40B Kazakh CPT Step200 |
| Repository 🤗 | https://huggingface.co/Eraly-ml/Kimi-K3-0.40B-Kazakh-CPT-step200 |
| Base Model(s) | |
| Model Size | 0.40b |
| Required VRAM | 0.8 GB |
| Updated | 2026-07-30 |
| Maintainer | Eraly-ml |
| Model Type | kimi_k3 |
| Model Files | |
| Supported Languages | kk en |
| Model Architecture | KimiK3ForConditionalGeneration |
| License | mit |
| Transformers Version | 5.14.1 |
| Tokenizer Class | TikTokenTokenizer |
| Padding Token | [PAD] |
Best Alternatives to Kimi K3 0.40B Kazakh CPT Step200
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Kimi K3 0.40B | 0K / 1.6 GB | 14080 | 35 |
Note: green Score (e.g. "73.2") means that the model is better than Eraly-ml/Kimi-K3-0.40B-Kazakh-CPT-step200 .
Rank the Kimi K3 0.40B Kazakh CPT Step200 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