Open-weight LLMs you can run yourself › Qwen3.8 Flash Next
Updated · public data
Alibaba · Open weights
Qwen3.8 Flash Next is an open-weight LLM from Alibaba with 180B parameters. It needs about 109 GB of memory at 4-bit — too big for one consumer device, so most people use it through a hosted provider.
| Parameters | 180B |
| Memory to run | ~109 GB (at 4-bit, rough estimate) |
| Downloads | 2.3M (last 30 days on Hugging Face) |
| Likes | 6.3K |
| License | Custom license |
| First uploaded | Aug 24, 2026 |
| Hosted from | $0.15 (per 1M input tokens · cheapest on OpenRouter) |
| Phone | iPhone · Android: too big |
| PC with a GPU | 8 GB: too big · 12 GB: too big · 16 GB: too big · 24 GB: too big · 32 GB: too big |
| PC or laptop, no GPU | 16 GB: too big · 32 GB: too big · 64 GB: too big |
| Mac | 16 GB: too big · 32 GB: too big · 64 GB: too big · 128 GB: too big |
huggingface.co/Qwen/Qwen3.8-Flash-Next
Data: Hugging Face (official accounts), Oct 16, 2026 · memory is a rough estimate (4-bit for LLMs, 8-bit for image and video, plus 10%) · hosted price: OpenRouter