DEV Community

#mlx

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Running released Next-Concept Modeling checkpoints on Apple Silicon
janmusic profile
Jan

Running released Next-Concept Modeling checkpoints on Apple Silicon

#mlx #opensource #python #machinelearning
Comments
6 min read
MiMo V2.6 Flash Local on Two Mac Studios vs Cloud: Benchmark
mihai_leanzero profile

MiMo V2.6 Flash Local on Two Mac Studios vs Cloud: Benchmark

#ai #mlx #benchmark #goose
Comments
16 min read
Apple's Foundation Models CLI: A First Look from Java
myfear profile

Apple's Foundation Models CLI: A First Look from Java

#java #mlx #ai #apple
Comments
8 min read
[AI] LM Studio Couldn't Run This Model, So I Got It Running On My Own Mac
gordonwei profile

[AI] LM Studio Couldn't Run This Model, So I Got It Running On My Own Mac

#mlx #macos #llm #python
Comments
7 min read
Best Local Image Generation Model on Mac: ERNIE vs FLUX
mihai_leanzero profile

Best Local Image Generation Model on Mac: ERNIE vs FLUX

#ai #mlx #macos #opensource
1
Comments
25 min read
vllm-mlx on Apple Silicon: Continuous Batching Works, but Unified Memory Sets the Real Limit
jangwook_kim_e31e7291ad98 profile

vllm-mlx on Apple Silicon: Continuous Batching Works, but Unified Memory Sets the Real Limit

#applesilicon #mlx #llmserving #continuousbatching
1
Comments 2
11 min read
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
kiarina profile

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
2
Comments
12 min read
Atlassian model v0.4: 21 of 25 Forge apps compile
mihai_leanzero profile

Atlassian model v0.4: 21 of 25 Forge apps compile

#machinelearning #llm #atlassian #mlx
Comments
13 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.