Qwen3.8 1.0B A0.6B is an open-source language model by inference-optimization. Features: 966.1m LLM, VRAM: 1.9GB, Context: 256K, License: mit, MoE, LLM Explorer Score: 0.35.
| LLM Name | Qwen3.8 1.0B A0.6B |
| Repository 🤗 | https://huggingface.co/inference-optimization/Qwen3.8-1.0B-A0.6B |
| Base Model(s) | |
| Model Size | 966.1m |
| Required VRAM | 1.9 GB |
| Updated | 2026-08-14 |
| Maintainer | inference-optimization |
| Model Type | qwen3_5_moe_text |
| Model Files | |
| Model Architecture | Qwen3_5MoeForCausalLM |
| License | mit |
| Context Length | 262144 |
| Model Max Length | 262144 |
| Transformers Version | 5.16.0.dev0 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 248320 |
| Errors | replace |