Run Qwen3.6-27B on Mac with oMLX: Fast Setup + Benchmarks — Full Guide + Benchmarks
8:23
Run Qwen3.6-27B on Mac with oMLX: Fast Setup + Benchmarks — Full Guide + Benchmarks
5.8K views3 weeks ago
YouTubeTech-Practice
Why massive LLMs fail during training (and how mHC fixes it)
8:21
Why massive LLMs fail during training (and how mHC fixes it)
79 views1 month ago
YouTubeTrellis Explainer
Episode #57 | My Framework Explained (MMXM Integration)
31:27
Episode #57 | My Framework Explained (MMXM Integration)
363 views3 weeks ago
YouTubefx4_living
Advanced MMXM Logic: Continuations
1:04:30
Advanced MMXM Logic: Continuations
9K views1 month ago
YouTubeAfyz
Run Local AI 2x Faster on Mac: MLX & oMLX Setup Guide
16:55
Run Local AI 2x Faster on Mac: MLX & oMLX Setup Guide
1.6K views2 weeks ago
YouTubeTony Xhepa
MLX Ling-2.6-Flash last bug fixed! I was going crazy when using it with OpenCode and pi mono, but now it works! 🚀Look at this video on M5 Max using 5bit quantization. 🥇 pi mono --> ULTRA FAST!🥈 OpenCode --> slower but detailed
2:25
MLX Ling-2.6-Flash last bug fixed! I was going crazy when using it with OpenCode and pi mono, but now it works! 🚀Look at this video on M5 Max using 5bit quantization. 🥇 pi mono --> ULTRA FAST!🥈 OpenCode --> slower but detailed
6.6K views2 weeks ago
x.comIvan Fioravanti ᯅ
I open-sourced DDTree-MLX: tree-based speculative decoding for Apple Silicon.Now you can run Qwen 3.5 27b on your Apple machines 1.5x faster than normal. Expect even faster on smaller models.It runs Qwen 3.5 27B locally with MLX, extends DFlash with draft trees, and gets ~10-15% faster than DFlash alone on code + structured prompts while keeping output lossless.Built on the works of @bstnxbt @liranringel @yaniv_romano
0:14
I open-sourced DDTree-MLX: tree-based speculative decoding for Apple Silicon.Now you can run Qwen 3.5 27b on your Apple machines 1.5x faster than normal. Expect even faster on smaller models.It runs Qwen 3.5 27B locally with MLX, extends DFlash with draft trees, and gets ~10-15% faster than DFlash alone on code + structured prompts while keeping output lossless.Built on the works of @bstnxbt @liranringel @yaniv_romano
34.3K views1 month ago
x.comThanh Pham
0:29
dflash-mlx: DFlash speculative decoding, ported to Apple Silicon.Qwen3-4B at 186 tok/s on a MacBook. 4.6× faster than plain MLX-LM. Exact greedy decoding: output matches plain target decoding.
123.3K views1 month ago
x.comArya Manjaramkar
0:41
.Also variants of Qwen3.5-s are ok, e.g. this works too$ dflash-serve --model kai-os/Carnice-9b --draft z-lab/Qwen3.5-9B-DFlash --port 8082@bstnxbt @kaiostephens - only had to add a single line to the MODEL_REMAPPING dict (lines 45-55; Claude did it):⏺ The fix needs to be applied to the installed mlx_lm package. Let me patch it:⏺ Update(~/python3-venv/torch313-metal/lib/python3.13/site-packages/mlx_lm/utils.py) ⎿  Added 1 line 50 "joyai_llm_flash": "deepseek_v3", 51 "kimi_k2": "deepseek_v3", 52
86.1K views1 month ago
x.comLjubomir Josifovski
2:03
A long time coming but new mlx-lm is here with better batching support in the server and Gemma 4.pip install -U mlx-lmHere is a video where a single M3 Ultra serves 5 opencode sessions with Gemma 4 26B that process ~130k tokens in ~1.5 minutes.
65K views1 month ago
x.comAngelos Katharopoulos
0:21
Nothing Fancy... just experimenting and exploring with the available ones before exploring the new trending ones.. The core trick here: ctx.measureText() pre-computes every word into a data object with a baseX, current x, and targetX. Each frame, a 120-segment dragon emits collision nodes with anatomically-computed radii. For every line of text, it projects each node onto the line's Y axis, compute the X exclusion span via √(r² - dy²), merge overlapping intervals, then run a relaxation solver (f
71K views1 month ago
x.comSHAHNAB AHMED
7:27
oMLX.AI：苹果硅芯上的AI加速引擎——本土化MLX服务器，融合智能SSD缓存与连续批处理，实现低延迟多模型推理，助力开发者无缝构建高效本地AI代理与编码工
8.4K views2 months ago
bilibili鲲鹏Talk
1:26
#NAME? Error in Excel
69.6K viewsMar 6, 2021
YouTubeAjay Anand
17:27
XFOIL Tutorial 5: Polar Plot Basics (Cl vs alpha, Cl vs Cd, Cm vs alpha, Cl vs xt/c)
61.1K viewsSep 25, 2018
YouTubethe Science of Flight
2:46
M4L : Build a MIDI Synth in 1 minute Pt 2 : ADSR~ envelope : Learning Max for Ableton live tutorial
23.3K viewsMar 5, 2011
YouTubeEric Ameres (eraserMice)
3:51
Realizing Infinite Array with Floquet Port and Unit Cell Analysis Using Ansys HFSS
8.4K viewsJul 16, 2021
YouTubeAnsys Learning
24:38
Neural Networks: Multi-Layer Perceptrons: Building a Brain From Layers of Neurons
77.4K viewsAug 18, 2018
YouTubeJacob Schrum
10:43
Microstrip Patch Antenna Finite Array Creation Using Domain Decomposition Method in Ansys HFSS
31K viewsNov 20, 2020
YouTubeAnsys Learning
32:37
拒绝“OpenClaw”焦虑！用“AI”视角拆解模型、硬件与部署框架，低配Mac也能跑出翻倍速度，顺便推荐工具oMLX，Mac电脑都用起来
24.1K views1 month ago
YouTube有什么好玩playfulsoul
1:42:48
XFLR5 Tutorial Series
3.7K views3 months ago
YouTubeSimulation Engineer
14:41
Foil Analysis in XFLR
3.3K viewsNov 7, 2024
YouTubeDr Kidd Engineering
10:36
Foil Batch Analysis
1.5K viewsNov 7, 2024
YouTubeDr Kidd Engineering
37:46
Multi Layer Perceptron | MLP Intuition
175.5K viewsMar 1, 2022
YouTubeCampusX
21:17
Suffix arrays: maximum skipping
2.2K viewsAug 10, 2022
YouTubeBen Langmead
14:46
But How Does The MultiLayer Perceptron Actually Work?
52.3K viewsJun 15, 2017
YouTubeOscar Alsing Ferreira
9:19
#XFLR5 Full flight analysis tutorial
21.9K viewsJun 16, 2015
YouTubeChristo T
3:02
2 Foil batch analysis
87.5K viewsJan 17, 2016
YouTubetechwinder
3:17
Electron Localization Function (ELF), Local Orbital Locator (LOL) and ESP Plot Using Multiwfn.
4.6K viewsOct 12, 2023
YouTubeResearch Point
24:18
Ctrl + Shift + Enter: Excel Array Formulas 19: Array Function: MMULT
24.2K viewsFeb 10, 2014
YouTubeexcelisfun
2:22
Excel Array Formula Series 12: MMULT function Matrix Algebra
45.5K viewsJun 26, 2008
YouTubeexcelisfun
See more