Ring Mini Linear 2.0 4bit is an open-source language model by mlx-community. Features: LLM, VRAM: 9.2GB, Context: 128K, License: mit, MoE, Quantized.
4-bit 4bit Bailing moe linear Base model:inclusionai/ring-mi... Base model:quantized:inclusion... Conversational Custom code En Mlx Moe Quantized Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlx-community/Ring-mini-linear-2.0-4bit
Ring Mini Linear 2.0 4bit Parameters and Internals
| LLM Name | Ring Mini Linear 2.0 4bit |
| Repository 🤗 | https://huggingface.co/mlx-community/Ring-mini-linear-2.0-4bit |
| Base Model(s) | |
| Required VRAM | 9.2 GB |
| Updated | 2026-03-27 |
| Maintainer | mlx-community |
| Model Type | bailing_moe_linear |
| Model Files | |
| Supported Languages | en |
| Quantization Type | 4bit |
| Model Architecture | BailingMoeLinearV2ForCausalLM |
| License | mit |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.56.1 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 157184 |
| Torch Data Type | bfloat16 |
Rank the Ring Mini Linear 2.0 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