Alibaba
Qwen2.5 Coder
code
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.
0.5B
8 GB card- Parameters
- 0,5B
- Q4_K_M file
- 0,4 Go
- Recommended VRAM
- ≥ 1,9 Go
- Max context
- 32 768
Not measured yet
1.5B
8 GB card- Parameters
- 1,5B
- Q4_K_M file
- 0,9 Go
- Recommended VRAM
- ≥ 2,4 Go
- Max context
- 32 768
Not measured yet
3B
8 GB card- Parameters
- 3,1B
- Q4_K_M file
- 1,8 Go
- Recommended VRAM
- ≥ 3,3 Go
- Max context
- 32 768
Not measured yet
7B
8 GB card- Parameters
- 7,6B
- Q4_K_M file
- 4,4 Go
- Recommended VRAM
- ≥ 5,9 Go
- Max context
- 32 768
Not measured yet
14B
12 GB card- Parameters
- 14,8B
- Q4_K_M file
- 8,4 Go
- Recommended VRAM
- ≥ 9,9 Go
- Max context
- 32 768
Not measured yet
32B
24 GB card- Parameters
- 32,8B
- Q4_K_M file
- 18,5 Go
- Recommended VRAM
- ≥ 20,0 Go
- Max context
- 32 768
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).