[GH-ISSUE #10260] The free deepseek from Silicon Mobility is better than the deepseek in Ollama? #68791

Open
opened 2026-05-04 15:11:51 -05:00 by GiteaMirror · 0 comments
Owner

Originally created by @jinwater88 on GitHub (Apr 14, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/10260

I am using deepseek-r1-7b to search the RAG local knowledge base. The free deepseek from Silicon Mobility is better than the deepseek in Ollama. Silicon Mobility's DeepSeek-R1-Distill-Qwen-7B is a model based on Qwen2.5-Math-7B through knowledge distillation. Yours is also based on Qwen2.5-Math-7B through knowledge distillation. Are there any other optimizations?

Originally created by @jinwater88 on GitHub (Apr 14, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/10260 I am using deepseek-r1-7b to search the RAG local knowledge base. The free deepseek from Silicon Mobility is better than the deepseek in Ollama. Silicon Mobility's DeepSeek-R1-Distill-Qwen-7B is a model based on Qwen2.5-Math-7B through knowledge distillation. Yours is also based on Qwen2.5-Math-7B through knowledge distillation. Are there any other optimizations?
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#68791