99% of locally deployed AI are not as good as Doubao
2000 yuan to play with Deepseek 671b? Thousand-yuan level Deepseek wave server solution
Local deployment of large models is really useless but really fun
Qwen3.8 is so powerful, I've been playing with it for days and just can't stop. So this is the wisdom of Lady Qianwen?
Speed secured! Quality secured! Capacity secured! Strada+KVMem+actKV+128K/256K/1M+3060Ti 8GiB+RAM 32GiB+XeonE5 2696v3
Qwen3.8 Titans Duel: How to Choose Between Full-Machine Flow Strata and Single-Card Flow NInfer
[In-depth Explainer] What do 8B, 14B, 32B, and 72B mean in large model names?
qwen3.8-flash-next-iq3_s is no longer just a toy; it's truly within reach for those on a budget. Under 10,000 yuan, it's the closest thing to a production-ready local model.
Test: Qwen3.8 Flash Next vs Qwen3.8 27B! Qwen3.8 Flash Next Effect
After deploying Qwen 3.8 27b, my DeepSeek can retire (or can it?)
Strata qwen3.8flash next truly a god-tier project! 512K ultra-long context for local deployment
God-level project Strata! Two V100s running Qwen3.8 Flash IQ3_S, tested at 60-100 tokens/s
deepseek called 28 sub-agents at the same time
Best Local AI Models for Each Archive Slot Recommendation! Full Coverage from 4GB to 32GB+, No More Hesitation After Watching
Local deployment of DeepSeek Harness plus Qwen3.8-27B tutorial, achieving token freedom! I also discovered an Easter egg in the source code by "Liang Sheng"!
Scared to tears! Qwen 3.8 27B's ridiculous performance; can you believe this is only a 27B model? | Small Wave Mom's Radar Chart
DeepSeek vs Claude: Does AI Have Self-Awareness? Opus 5.5 Remastered
180B squeezed into 22G: Strata × Qwen 3.8 Flash × 2080Ti three-piece set actual test
Qwen3.8 Flash Next × Strata, tested on a single 5090
35B MoE isn't over yet: Occamy-1.0, let Qwen3.6 35B-A3B evolve further!
