From civitai/fannon: https://civitai.com/models/1036874/fn-mix-noob-xl?modelVersionId=1416736
Based on my experience, Q4_K_S and Q4_K_M are usually the balance points between model size, quantization, and speed.
In some benchmarks, selecting a large-parameter low-quantization LLM tends to perform better than a small-parameter high-quantization LLM.
根据我的经验,通常Q4_K_S、Q4_K_M是模型尺寸/量化/速度的平衡点
在某些基准测试中,选择大参数低量化模型往往比选择小参数高量化模型表现更好。
您有惊人的硬件??!
我正在使用16G DDR内存和R5 5600进行基于兴趣的量化工作,以及50Mbps的带宽速度,可能会无法为更高参数的模型进行量化。
- Downloads last month
- 11
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no library tag.
Model tree for btaskel/Fn-Mix-Noob-XL-1.66-GGUF
Base model
Laxhar/noobai-XL-0.5
Finetuned
Laxhar/noobai-XL-0.6
Finetuned
Laxhar/noobai-XL-0.75
Finetuned
Laxhar/noobai-XL-0.77
Finetuned
Laxhar/noobai-XL-1.0
Finetuned
John6666/fn-mix-noob-xl-v166-sdxl