Skip to content
Navigation menu
Search
Powered by Algolia
Search
Log in
Create account
DEV Community
Close
#
speculativedecoding
Follow
Hide
Posts
Left menu
đź‘‹
Sign in
for the ability to sort posts by
relevant
,
latest
, or
top
.
Right menu
Qwen3.8-27B on one RTX 3090, and the setting its README says chat clients should leave at default
Reno Lu
Reno Lu
Reno Lu
Follow
Oct 2
Qwen3.8-27B on one RTX 3090, and the setting its README says chat clients should leave at default
#
vllm
#
localllm
#
speculativedecoding
#
quantization
Comments
Add Comment
4 min read
Muse Glimmer: il modello “agentico” open source di Meta che vuole accesso profondo alla tua vita (anche in locale)
frontendfacile.it
frontendfacile.it
frontendfacile.it
Follow
Aug 13
Muse Glimmer: il modello “agentico” open source di Meta che vuole accesso profondo alla tua vita (anche in locale)
#
llmondevice
#
quantizzazione4bit
#
speculativedecoding
#
modelliagentici
Comments
Add Comment
4 min read
Exploring DeepSpec: Insights for Developers in Speculative Decoding
David DĂaz
David DĂaz
David DĂaz
Follow
Jul 7
Exploring DeepSpec: Insights for Developers in Speculative Decoding
#
speculativedecoding
#
python
#
ai
#
deepspec
Comments
Add Comment
4 min read
đź‘‹
Sign in
for the ability to sort posts by
relevant
,
latest
, or
top
.
We're a place where coders share, stay up-to-date and grow their careers.
Log in
Create account