Commit Beelink mini defaults: CPU inference, 32k context
Stop forcing Vulkan NGL in compose override (that overrode .env). Raise mini profile context to 32768 for ~28–32GB RAM hosts.
This commit is contained in:
parent
84a0945b10
commit
7e5444a177
2 changed files with 7 additions and 17 deletions
|
|
@ -5,7 +5,8 @@ STACK_PROFILE=mini
|
|||
# Ternary-Bonsai 27B fits in system RAM; keep CPU
|
||||
BONSAI_BACKEND=cpu
|
||||
BONSAI_NGL=0
|
||||
BONSAI_CTX=16384
|
||||
# 32k uses free system RAM well on ~32GB mini PCs (weights ~7GB)
|
||||
BONSAI_CTX=32768
|
||||
BONSAI_KV4=0
|
||||
BONSAI_THREADS=12
|
||||
BONSAI_TEMP=0.7
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue