Qwen3.8 Flash Next DERISKED W4A16 AWQ is an open-source language model by davetha. Features: 20.7b LLM, VRAM: 71.8GB, License: other, Quantized, LLM Explorer Score: 0.29.
| LLM Name | Qwen3.8 Flash Next DERISKED W4A16 AWQ |
| Repository 🤗 | https://huggingface.co/davetha/Qwen3.8-Flash-Next-DERISKED-W4A16-AWQ |
| Base Model(s) | |
| Model Size | 20.7b |
| Required VRAM | 71.8 GB |
| Updated | 2026-09-01 |
| Maintainer | davetha |
| Model Type | qwen4_exp |
| Model Files | |
| AWQ Quantization | Yes |
| Quantization Type | awq |
| Model Architecture | Qwen4ExpForConditionalGeneration |
| License | other |
| Model Max Length | 262144 |
| Transformers Version | 5.16.1 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Errors | replace |