Kimi Linear 48B A3B Instruct 4bit is an open-source language model by mlx-community. Features: 48b LLM, VRAM: 27.6GB, License: mit, Quantized, Instruction-Based.
4-bit 4bit Base model:moonshotai/kimi-lin... Base model:quantized:moonshota... Conversational Custom code Instruct Kimi linear Mlx Quantized Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlx-community/Kimi-Linear-48B-A3B-Instruct-4bit
Kimi Linear 48B A3B Instruct 4bit Parameters and Internals
| LLM Name | Kimi Linear 48B A3B Instruct 4bit |
| Repository 🤗 | https://huggingface.co/mlx-community/Kimi-Linear-48B-A3B-Instruct-4bit |
| Base Model(s) | |
| Model Size | 48b |
| Required VRAM | 27.6 GB |
| Updated | 2026-03-27 |
| Maintainer | mlx-community |
| Model Type | kimi_linear |
| Instruction-Based | Yes |
| Model Files | |
| Quantization Type | 4bit |
| Model Architecture | KimiLinearForCausalLM |
| License | mit |
| Model Max Length | 1048576 |
| Transformers Version | 4.57.1 |
| Tokenizer Class | TikTokenTokenizer |
| Padding Token | [PAD] |
| Vocabulary Size | 163840 |
Best Alternatives to Kimi Linear 48B A3B Instruct 4bit
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Kimi Linear 48B A3B Instruct | 0K / 98.3 GB | 54270 | 555 |
Rank the Kimi Linear 48B A3B Instruct 4bit 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? 51648 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260327b