Deepseek beats Qwen in Design with 10% of the token cost
Model tested - Models : DeepSeek V4.1 Flash and Qwen3.8-Flash, head to head both run through omp / opencode-go - Use case : coding - a real feature on my hackat
Alibaba's fast, cheap open-weight multimodal model (Qwen 3.8 family) with 1M context, deep thinking, and agentic coding — the budget Flash sibling to Qwen 3.8 Max.
“Qwen3.8-next-flash is impressive though, especially with Strata or Basalt as inference engines. On a 5090 laptop with 64GB RAM one can run NVFP4 quants at 120-140t/s decode and 3000-4000t/s prefill.”
“Just reading chain of thought traces for Agda (I'm using Qwen 3.8-Flash-Next) and it's struggling so hard with just the syntax, long before it can struggle with semantics or type errors.”
“Flash next is the best model overall but it is very (overly) zealous and can get itself off on tiresome tangential tasks mid-turn. It's just too eager to let it run alone on longer-horizon coding tasks.”
Sí — Qwen 3.8 Flash tiene una puntuación worth-it del 57%, basada en 203 votos de la comunidad.
Qwen 3.8 Flash es un modelo de Chat. Sparse and fast — only 6B active parameters, decoding at 150 tps on a single consumer GPU.
$0.11 / $0.38 per 1M tokens
Model tested - Models : DeepSeek V4.1 Flash and Qwen3.8-Flash, head to head both run through omp / opencode-go - Use case : coding - a real feature on my hackat