VOOZH
about
URL: https://dev.to/t/mlx
⇱ Mlx - DEV Community
DiffusionGemma 26B 登陸 M2 Max：MLX 吞吐量實測與 Context 極限挑戰
👁 jh5_pulse profile
JH5
👁 Image
JH5
Jun 19
DiffusionGemma 26B 登陸 M2 Max：MLX 吞吐量實測與 Context 極限挑戰
#
ai
#
benchmark
#
diffusiongemma
#
mlx
Add Comment
3 min read
Meet mlx-code: A Composable, Git-Isolated Coding Agent Built for Mac
👁 josef_albers_fc59b610c5de profile
Josef Albers
👁 Image
Josef Albers
Jun 1
Meet mlx-code: A Composable, Git-Isolated Coding Agent Built for Mac
#
ai
#
mlx
#
python
#
agents
Add Comment
3 min read
I Blamed the Model for Months. The Bug Was My Sampler.
👁 sleepyquant profile
SleepyQuant
👁 Image
SleepyQuant
May 29
I Blamed the Model for Months. The Bug Was My Sampler.
#
applesilicon
#
mlx
#
localai
#
m1max
Add Comment
4 min read
Qwen 3.6 enable_thinking — The MoE Pitfall That Broke My Agent JSON Parsing
👁 sleepyquant profile
SleepyQuant
👁 Image
SleepyQuant
May 18
Qwen 3.6 enable_thinking — The MoE Pitfall That Broke My Agent JSON Parsing
#
qwen
#
mlx
#
localai
#
llminference
Add Comment
5 min read
Running Qwen3.6-27B on a 16GB M1 MacBook Pro: A Practical Engineer’s Guide
👁 mike_anderson_d01f52129fb profile
Mike Anderson
👁 Image
Mike Anderson
May 18
Running Qwen3.6-27B on a 16GB M1 MacBook Pro: A Practical Engineer’s Guide
#
ai
#
apple
#
qwen
#
mlx
Add Comment
7 min read
Running Qwen3.6-27B on a 16GB M1 MacBook Pro: A Practical Engineer’s Guide
👁 mike_anderson_d01f52129fb profile
Mike Anderson
👁 Image
Mike Anderson
May 18
Running Qwen3.6-27B on a 16GB M1 MacBook Pro: A Practical Engineer’s Guide
#
ai
#
apple
#
qwen
#
mlx
Add Comment
7 min read
What 19 GB of Memory Compression Taught Me About MLX on M1 Max
👁 sleepyquant profile
SleepyQuant
👁 Image
SleepyQuant
Apr 20
What 19 GB of Memory Compression Taught Me About MLX on M1 Max
#
mlx
#
ai
#
machinelearning
#
python
Add Comment
7 min read
Why Apple Silicon Quietly Won the Local-AI Race (April 2026)
👁 sleepyquant profile
SleepyQuant
👁 Image
SleepyQuant
Apr 18
Why Apple Silicon Quietly Won the Local-AI Race (April 2026)
#
ai
#
mlx
#
machinelearning
#
python
Add Comment
6 min read
SleepyQuant – a 12-agent crypto quant running on one Mac
👁 sleepyquant profile
SleepyQuant
👁 Image
SleepyQuant
Apr 18
SleepyQuant – a 12-agent crypto quant running on one Mac
#
ai
#
mlx
#
python
#
buildinpublic
Add Comment
3 min read
The Inverted Control: What 24 Hours of Running Our Own Bot Backwards Revealed
👁 sleepyquant profile
SleepyQuant
👁 Image
SleepyQuant
Apr 18
The Inverted Control: What 24 Hours of Running Our Own Bot Backwards Revealed
#
ai
#
mlx
#
python
#
buildinpublic
Add Comment
7 min read
Gemma 4 on Apple Silicon: 85 tok/s with a pip install
👁 raullen_chai_76e18e9705b0 profile
Raullen Chai
👁 Image
Raullen Chai
Apr 7
Gemma 4 on Apple Silicon: 85 tok/s with a pip install
#
gemma4
#
applesilicon
#
mlx
#
localai
👁 Image
1
reaction
Add Comment
4 min read
Ollama Just Got 93% Faster on Mac. Here's How to Enable It.
👁 alanwest profile
Alan West
👁 Image
Alan West
Apr 6
Ollama Just Got 93% Faster on Mac. Here's How to Enable It.
#
ollama
#
mlx
#
applesilicon
#
localinference
👁 Image
13
reactions
Add Comment
5 min read
👋
Sign in
for the ability to sort posts by
relevant
,
latest
, or
top
.
👁 DEV Community
We're a place where coders share, stay up-to-date and grow their careers.
Log in
Create account
👁 Image
👁 Image
👁 Image
👁 Image
👁 Image
