mirror of
https://github.com/ollama/ollama.git
synced 2026-03-09 07:16:38 -05:00
update context length format.
This commit is contained in:
@@ -6,9 +6,9 @@ Context length is the maximum number of tokens that the model has access to in m
|
||||
|
||||
<Note>
|
||||
Ollama defaults to the following context lengths based on VRAM:
|
||||
- < 24 GiB VRAM: 4,096 context
|
||||
- 24-48 GiB VRAM: 32,768 context
|
||||
- >= 48 GiB VRAM: 262,144 context
|
||||
- < 24 GiB VRAM: 4k context
|
||||
- 24-48 GiB VRAM: 32k context
|
||||
- >= 48 GiB VRAM: 256k context
|
||||
</Note>
|
||||
|
||||
Tasks which require large context like web search, agents, and coding tools should be set to at least 64000 tokens.
|
||||
|
||||
Reference in New Issue
Block a user