metadata
library_name: exllamav3
license: apache-2.0
license_link: https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct/blob/main/LICENSE
pipeline_tag: text-generation
base_model: Qwen/Qwen3-Coder-480B-A35B-Instruct
base_model_relation: quantized
tags:
- exl3
Exllamav3 quantization of Qwen/Qwen3-Coder-480B-A35B-Instruct
2.00 bpw h6 114.396 GiB
3.00 bpw h6 170.069 GiB
The 2.00bpw quant will fit in six 24 GB cards with 40k of fp16 context.