Qwen 3.8 27B ROCmFP4 FAST GGUF is an open-source language model by julianmb. Features: 27b LLM, VRAM: 9.2GB, License: apache-2.0, Quantized.
| LLM Name | Qwen 3.8 27B ROCmFP4 FAST GGUF |
| Repository 🤗 | https://huggingface.co/julianmb/Qwen-3.8-27B-ROCmFP4-FAST-GGUF |
| Model Name | Qwen 3.8 27B ROCmFP4 FAST |
| Base Model(s) | |
| Model Size | 27b |
| Required VRAM | 9.2 GB |
| Updated | 2026-08-17 |
| Maintainer | julianmb |
| Model Files | |
| Supported Languages | en zh |
| GGUF Quantization | Yes |
| Quantization Type | gguf|q3 |
| Model Architecture | MambaSSM |
| License | apache-2.0 |