Qwen3.8 27B MTP Bf16 is an open-source language model by mlx-community. Features: 27b LLM, VRAM: 0.8GB, License: apache-2.0, LLM Explorer Score: 0.36.
| LLM Name | Qwen3.8 27B MTP Bf16 |
| Repository 🤗 | https://huggingface.co/mlx-community/Qwen3.8-27B-MTP-bf16 |
| Base Model(s) | |
| Model Size | 27b |
| Required VRAM | 0.8 GB |
| Updated | 2026-08-15 |
| Maintainer | mlx-community |
| Model Type | qwen3_5_mtp |
| Model Files | |
| Supported Languages | en |
| License | apache-2.0 |
| Model Max Length | 262144 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Errors | replace |