Skip to content
Navigation menu
Search
Powered by Algolia
Search
Log in
Create account
DEV Community
Close
#
mlx
Follow
Hide
Posts
Left menu
đź‘‹
Sign in
for the ability to sort posts by
relevant
,
latest
, or
top
.
Right menu
Running Qwen3.8-Flash-Next on a 128 GB Mac: The Expert-Pruning Trap, and a Memory-Mapped n-gram Table That Gets You to 240K Tokens
Nariaki Wada
Nariaki Wada
Nariaki Wada
Follow
Sep 24
Running Qwen3.8-Flash-Next on a 128 GB Mac: The Expert-Pruning Trap, and a Memory-Mapped n-gram Table That Gets You to 240K Tokens
#
mlx
#
llm
#
applesilicon
#
machinelearning
Comments
Add Comment
12 min read
Fine-tune Qwen3.8-27B with MLX LoRA on a Mac
Mihai Perdum
Mihai Perdum
Mihai Perdum
Follow
Sep 17
Fine-tune Qwen3.8-27B with MLX LoRA on a Mac
#
machinelearning
#
mlx
#
tutorial
#
llm
Comments
Add Comment
57 min read
Atlassian model v0.4: 21 of 25 Forge apps compile
Mihai Perdum
Mihai Perdum
Mihai Perdum
Follow
Sep 17
Atlassian model v0.4: 21 of 25 Forge apps compile
#
machinelearning
#
llm
#
atlassian
#
mlx
Comments
Add Comment
13 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
