Qwen3.8 Flash Next MXFP4 FP8 GPTQ is an open-source language model by tcclaviger. Features: 175.4b LLM, VRAM: 5.4GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.35.
| LLM Name | Qwen3.8 Flash Next MXFP4 FP8 GPTQ |
| Repository 🤗 | https://huggingface.co/tcclaviger/Qwen3.8-Flash-Next-MXFP4-FP8-GPTQ |
| Base Model(s) | |
| Model Size | 175.4b |
| Required VRAM | 5.4 GB |
| Updated | 2026-09-16 |
| Maintainer | tcclaviger |
| Model Type | qwen4_exp |
| Model Files | |
| GPTQ Quantization | Yes |
| Quantization Type | gptq |
| Model Architecture | Qwen4ExpForConditionalGeneration |
| License | apache-2.0 |
| Model Max Length | 262144 |
| Transformers Version | 5.8.0.dev0 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Errors | replace |