ModelHub XC a1fdd9d25d 初始化项目,由ModelHub XC社区提供模型
Model: Melvin56/DeepSeek-R1-ReDistill-Qwen-7B-v1.1-GGUF
Source: Original Platform
2026-09-16 19:26:19 +08:00

base_model, library_name, tags, language, pipeline_tag
base_model library_name tags language pipeline_tag
mobiuslabsgmbh/DeepSeek-R1-ReDistill-Qwen-7B-v1.1
transformers
DeepSeek-R1-Distill-Qwen-7B
en
text-generation

Melvin56/DeepSeek-R1-ReDistill-Qwen-7B-v1.1-GGUF

Original Model : mobiuslabsgmbh/DeepSeek-R1-ReDistill-Qwen-7B-v1.1

All quants are made using the imatrix option

Model Size (GB) Params
Q2_K_S 2.82 GB 7.62B
Q2_K 3.01 GB 7.62B
Q3_K_M 3.80 GB 7.62B
Q3_K_M 3.80 GB 7.62B
Q4_0 4.43 GB 7.62B
Q4_K_M 4.68 GB 7.62B
Q5_K_M 5.45 GB 7.62B
Q6_K 6.25 GB 7.62B
Q8_0 8.10 GB 7.62B
F16 15.23 GB 7.62B
Description
Model synced from source: Melvin56/DeepSeek-R1-ReDistill-Qwen-7B-v1.1-GGUF
Readme 26 KiB