Parallax

97 posts

Parallax banner
Parallax

Parallax

@tryParallax

build your own ai cluster. run open models across your machines.

Katılım Aralık 2025
39 Takip Edilen1.5K Takipçiler
Parallax retweetledi
rw ./
rw ./@gradientintern·
you can also run the latest and best models of GLM 5.2 on Parallax 👀 run locally with both macs and gpus together or solo with @tryParallax
rw ./ tweet media
Gradient@Gradient_HQ

A self-evolving agent + a 428B model + 3 Macs = ? Your own AI lab. We ran @MiniMax_AI M3 locally with @tryParallax, right on our desk. Then @GA_agent_ai took over to create a 5-stock portfolio and write it to disk. No cloud. No API bills. Nothing left the machine. Wild to see a ~3K-line agent drive all this with a 400B+ model on local hardware. Thanks to the GenericAgent and MiniMax teams for making local AI feel real.

English
9
9
55
4.1K
Parallax retweetledi
MiniMax (official)
MiniMax (official)@MiniMax_AI·
This is a glimpse of where local AI is heading and we are glad to be part of it. Really impressive work by all the teams involved @Gradient_HQ, @tryParallax, and @GA_agent_ai
Gradient@Gradient_HQ

A self-evolving agent + a 428B model + 3 Macs = ? Your own AI lab. We ran @MiniMax_AI M3 locally with @tryParallax, right on our desk. Then @GA_agent_ai took over to create a 5-stock portfolio and write it to disk. No cloud. No API bills. Nothing left the machine. Wild to see a ~3K-line agent drive all this with a 400B+ model on local hardware. Thanks to the GenericAgent and MiniMax teams for making local AI feel real.

English
27
58
1.3K
113.5K
Parallax
Parallax@tryParallax·
our goal stays the same: turn the machines on your desk into one local serving layer for powerful open models. in this demo, we run @MiniMax_AI M3 across local Macs and powers @GA_agent_ai through localhost. no hosted endpoint. no remote API. everything on device.
Gradient@Gradient_HQ

A self-evolving agent + a 428B model + 3 Macs = ? Your own AI lab. We ran @MiniMax_AI M3 locally with @tryParallax, right on our desk. Then @GA_agent_ai took over to create a 5-stock portfolio and write it to disk. No cloud. No API bills. Nothing left the machine. Wild to see a ~3K-line agent drive all this with a 400B+ model on local hardware. Thanks to the GenericAgent and MiniMax teams for making local AI feel real.

English
1
5
20
1.1K
Parallax retweetledi
Yuan ./
Yuan ./@yuangao·
Thrilled to see @tryParallax live in production on @Theta_Network. This is exactly why @Gradient_HQ built Parallax: turning the world’s GPU mesh into a sovereign, distributed token factory. Congrats on the milestone! 🫡
Theta Network@Theta_Network

To make this work, we adapted Parallax, @Gradient_HQ's distributed inference framework, to run across EdgeCloud's global node network. One API endpoint, model split across many machines, no centralized cluster required.

English
25
66
369
47.3K
Parallax
Parallax@tryParallax·
glad we could help! with the agentic adoption soaring, privacy and token cost are already the top concerns for both agent and human users. that's what parallax's built for.
Theta Network@Theta_Network

To make this work, we adapted Parallax, @Gradient_HQ's distributed inference framework, to run across EdgeCloud's global node network. One API endpoint, model split across many machines, no centralized cluster required.

English
17
38
215
27.8K
Theta Network
Theta Network@Theta_Network·
To make this work, we adapted Parallax, @Gradient_HQ's distributed inference framework, to run across EdgeCloud's global node network. One API endpoint, model split across many machines, no centralized cluster required.
English
11
33
265
98.8K
Theta Network
Theta Network@Theta_Network·
Qwen3 32B by Alibaba is now live on Theta EdgeCloud as a decentralized on-demand inference API, a large-scale LLM served across community GPU nodes using pipeline parallelism over the internet. 🧵
Theta Network tweet mediaTheta Network tweet media
English
24
114
504
46.4K
Parallax
Parallax@tryParallax·
@VitalikButerin buy a GPU, get together a group of friends. don’t carry the world on your own shoulders. we’ve been building this for a while. try parallax for local ai.
English
1
0
13
1.8K
Parallax
Parallax@tryParallax·
@RoundtableSpace 35b model on a macbook with compressed cache is a solid result. local inference keeps getting more accessible and it's fun to watch people push the limits of what consumer hardware can do!
English
0
0
4
231
0xMarioNawfal
0xMarioNawfal@RoundtableSpace·
A solo dev rebuilt Google’s new algorithm with Claude in 7 days, made it 3.7x faster, and got a 35B model running on a MacBook with 4.6x compressed cache. Google published the paper. He shipped the code.
0xMarioNawfal tweet media
English
64
192
2.5K
252.4K
Parallax
Parallax@tryParallax·
@adrgrondin @PrismML 1-bit model running at 40 tok/s on an iphone. mlx is making on-device inference surprisingly usable now.
English
0
0
6
564
Adrien Grondin
Adrien Grondin@adrgrondin·
Demo of 1-bit Bonsai 8B from @PrismML running on-device on iPhone 17 Pro More than 40tk/s for a dense 8B model on iPhone, that’s a first Powered by Apple MLX and available now in Locally AI
English
46
119
1.8K
160.1K
Parallax
Parallax@tryParallax·
@ollama local llm + mlx is a great combo! apple silicon keeps getting better for local inference and it's nice to see more players in the ecosystem lean into it properly.
English
1
0
6
197
ollama
ollama@ollama·
Ollama is now updated to run the fastest on Apple silicon, powered by MLX, Apple's machine learning framework. This change unlocks much faster performance to accelerate demanding work on macOS: - Personal assistants like OpenClaw - Coding agents like Claude Code, OpenCode, or Codex
English
294
723
5.8K
787.7K
Parallax
Parallax@tryParallax·
@tom_doerr single binary, self-hosted, no dependencies. this is the way local ai should ship. less config, more building.
English
1
0
6
59
Parallax
Parallax@tryParallax·
@karaage0703 9bから27bへのローカル性能の差がすごい。qwen3.5は今セルフホストするなら最高のモデルの一つ。特に異なるデバイス間でシャーディングするなら。
日本語
1
0
6
146
からあげ
からあげ@karaage0703·
自分の用途で、DGX Sparkで動かした感じだとQwen3.5 27Bの方が9Bより圧倒的によいですね。用途や環境で体感ことなるものなのですね > Qwen3.5の27Bが9Bに負けた RTX 4060の逆説｜ぷらずもん zenn.dev/plasmon/articl… #zenn
日本語
3
17
149
16.3K
Parallax
Parallax@tryParallax·
TurboQuant tackles one bottleneck: KV cache memory. there's another one that matters just as much in distributed setups: communication latency between nodes. we built Decentralized Speculative Decoding (DSD) to turn that idle network wait time into useful computation, 2.56x speedup on HumanEval, no retraining needed. combine cache compression with latency compression and local inference starts looking very different. arxiv.org/abs/2511.11733
English
6
3
20
572
Shay Boloor
Shay Boloor@StockSavvyShay·
$GOOGL just released TurboQuant which is a new compression method that can cut LLM cache memory by at least 6x & deliver ~8x speedups without sacrificing quality This could make local AI inference far more capable with larger context windows & less memory strain across devices
GIF
English
53
88
704
759.3K
Parallax
Parallax@tryParallax·
hf-mount solves the storage side: any model, mounted locally like a drive. the next piece is actually running those models across whatever hardware you have. that's what parallax does: schedule inference across a pool of heterogeneous GPUs so the model doesn't just live on your machine, it runs there too. mount + serve, fully local.
English
0
0
1
141
clem 🤗
clem 🤗@ClementDelangue·
Local AI is free, fast & secure! So today we're introducing hf-mount: attach any storage bucket, model or dataset from @huggingface as a local filesystem. This is a game changer, as it allows you to attach remote storage that is 100x bigger than your local machine's disk. This is also perfect for Agentic storage!! Let's go!
clem 🤗 tweet media
English
67
220
1.3K
253.5K
Parallax
Parallax@tryParallax·
@oprydai you don't need to go into debt though. a couple of mac minis or an nvidia card can already run serious models locally. parallax lets you connect whatever hardware you have into one cluster. start small, add devices as you go. the whole point is using what's already on your desk.
English
0
0
4
63
Mustafa
Mustafa@oprydai·
get into debt if you must, but build a hardware home lab.
Mustafa tweet media
English
43
67
1.2K
32.3K
Parallax
Parallax@tryParallax·
@openclaw solid release. deepseek provider plugin + qwen pay-as-you-go opens up a lot of new local setups. parallax users running openclaw stacks should have a smoother time with this one.
English
0
0
6
1.5K
OpenClaw🦞
OpenClaw🦞@openclaw·
OpenClaw 2026.3.23 🦞 🧪 DeepSeek provider plugin ☁️ Qwen pay-as-you-go ♻️ OpenRouter auto pricing + Anthropic thinking order 🖥️ Chrome MCP waits for tabs 🔧 Discord/Slack/Matrix + Web UI fixes Upgrade before your agent does it for you. github.com/openclaw/openc…
English
217
215
2.4K
375.3K

Keşfet

@Gradient_HQ @GA_agent_ai @MiniMax_AI @Theta_Network @VitalikButerin @RoundtableSpace @adrgrondin @PrismML