Qwen3 MoE 4x0.6B 2.4B Reasoning V1 Full is an open-source language model by leeminwaan. Features: 1.4b LLM, VRAM: 2.8GB, Context: 40K, MoE, LLM Explorer Score: 0.2.
| LLM Name | Qwen3 MoE 4x0.6B 2.4B Reasoning V1 Full |
| Repository 🤗 | https://huggingface.co/leeminwaan/Qwen3-MOE-4x0.6B-2.4B-reasoning-v1-full |
| Model Size | 1.4b |
| Required VRAM | 2.8 GB |
| Updated | 2026-08-07 |
| Maintainer | leeminwaan |
| Model Type | qwen3_moe |
| Model Files | |
| Model Architecture | Qwen3MoeForCausalLM |
| Context Length | 40960 |
| Model Max Length | 40960 |
| Transformers Version | 4.52.4 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|im_end|> |
| Vocabulary Size | 151936 |
| Torch Data Type | float16 |
| Errors | replace |