Alibaba

Qwen3.8

Pick a size: the video memory shown is the Q4_K_M file (the protocol's quantisation) plus about 1.5 GB for a 4,000-token context.

27B

24 GB card
Parameters
27,8B
Q4_K_M file
16,2 Go
Recommended VRAM
≥ 17,7 Go
Max context
262 144

Not measured yet

Flash-Next

> 32 GB
Parameters
180B
Q4_K_M file
111,4 Go
Recommended VRAM
≥ 112,9 Go
Max context
262 144

Not measured yet

MoE (“30B-A3B”): all the memory of a 30B, but the speed of a model with 3B active parameters. “> 32 GB”: several cards, or part of the model in system memory (much slower).