cd/entity/DeepSeek 7B· home› entities› DeepSeek 7B
grep -l @deepseek 7b /news/*.json | wc -l → 1

DeepSeek 7B

mentions 1 type Person feed RSS

// recent coverage 1 mentions

13:45
2026-08-04
promptcube3.com
large-language-models

Homebench: Local LLM Benchmark Results Across Speed, Memory

Homebench, a local LLM benchmarking tool, tested five models on an RTX 3060 12GB, finding Qwen 2.5 7B fastest at ~58 tokens/sec and LLaMA 3 8B highest quality at 8.2/10, while Mistral Nemo 12B underpe…

// co-occurs with top 7 entities
Homebench 1 Qwen 2.5 7B 1 LLaMA 3 8B 1 Mistral Nemo 12B 1 Gemma 2 9B 1 RTX 3060 1 llama.cpp 1
// topics top 3 topics
large language models 1 ai tools 1 ai research 1