ByteShape @ByteShape
Accelerating AI by Learning Optimal Datatypes byteshape.com Canada Joined October 2024-
Tweets22
-
Followers96
-
Following7
-
Likes26
We released Qwen 3.6 35B A3B GGUF quants in both NTP and MTP. The benchmark results made one thing clear: size, speed, and quality do not move in a straight line. GPU-5 was hard to beat. If it fits, try it first. Blog: byteshape.com/blogs/Qwen3.6-…
@KC_goes_digital We have them on our radar. Our models are optimized for the best quality vs speed/size tradeoff. We benchmark on real tasks and measure performance across different hardware, so it’s easier to find what actually works best on your setup.
We recently released our Qwen 3.5 35B A3B quants. If your setup can run GPU-7, you should try it. If not, we’ve got options across all hardware. Pi → 5090. Blog: byteshape.com/blogs/Qwen3.5-…
@therealsol4ra Regardless, we're happy for everyone to perform independent evaluations of our models and test them out for yourselves! We're highly confident in their quality!
@therealsol4ra KLD is a distribution deviation metric measuring in this case the deviation in token generation between quants and the original model. However, it does not measure behaviour, like the model taking a different path to solve the same problem than the original model for example.
@Yeely1310 @ravikiran_dev7 We're glad our quants are not falling for that👀
+ Hermes Agent + Qwen3.5 35B A3B + 4x parallel agents with 262k context window (each) + Over 200 t/s token generation + 3000 t/s prefill + 23.2GB total VRAM consumption on RTX 5090 It can take 5 parallel agents, 4 was the sweet spot with 2x in completion time vs 1.74x. Dream inference. @NousResearch @ByteShape
@ByteShape Qwen3.5-35B-A3B-IQ4_XS-4.12bpw.gguf is lethal. It was the most efficient Qwen3.5 35B-A3B, consuming only 23GB VRAM at FULL native context, on a RTX 5090 with -b and -ub 256. Just shy of 20 noisy points from UD-Q6_K_XL and a minute slower. However, Unsloth's was
Run your own local AI coding agent We just published a beginner guide for using @opencode with local models (@lmstudio, llama.cpp, @ollama). Mac, Linux, WSL2, full setup + API + config. byteshape.com/blogs/tutorial… From “I have a model” → “I have a working coding agent”
GPUs are consistent. CPUs are not. With our ByteShape Qwen 3.5 9B quants, the same models perform well across GPUs, but CPUs each have their own “favorites”. No one-size-fits-all. Optimize for your hardware. byteshape.com/blogs/Qwen3.5-…
ByteShape was quietly launched just before the year end. Two weeks ago, we announced our investment in the company. Since its launch, and with minimal fanfare on purpose, @ByteShape cumulative downloads have easily blown past 100,000. No small feat for a new startup!
Announcing @twosmallfishvc's investment in @ByteShape. In short, ByteShape is delivering step-function gains in AI efficiency, including up to 7x faster training, up to 10x faster inference, plus up to 40% compression to reduce model size.
Excellent quantisation on Devstral Small 2
We released ShapeLearn-optimized GGUFs for: • Devstral Small 2 24B, tuned for RTX 40/50 GPUs • Qwen3 Coder 30B, runs everywhere, yes even the Pi Maximum quality. Fastest TPS. Minimal compromise. GGUFs + interactive plots are live: byteshape.com/blogs/Devstral…
We released ShapeLearn-optimized GGUFs for: • Devstral Small 2 24B, tuned for RTX 40/50 GPUs • Qwen3 Coder 30B, runs everywhere, yes even the Pi Maximum quality. Fastest TPS. Minimal compromise. GGUFs + interactive plots are live: byteshape.com/blogs/Devstral…
Edge computing is getting spicy! Shoutout to @geerlingguy for showcasing our model. Love seeing what the community is building and how hard it’s being pushed. Clip: youtube.com/watch?v=jRQaur…
Raspberry Pi has a new AI HAT. This time with built-in 8 GB of RAM, so you can run machine vision + LLM inference all without touching the Pi's CPU. It's $130 and a little bit of a niche item. Find out why in my video: youtube.com/watch?v=jRQaur…
Raspberry Pi has a new AI HAT. This time with built-in 8 GB of RAM, so you can run machine vision + LLM inference all without touching the Pi's CPU. It's $130 and a little bit of a niche item. Find out why in my video: youtube.com/watch?v=jRQaur…
A 30B Qwen Model Walks into a Raspberry Pi and Runs in Real Time #HackerNews byteshape.com/blogs/Qwen3-30…
Eduardo Büll @EduardoBull
57 Followers 51 Following
kidd_lh @kidd_lh
30 Followers 324 Following
odi ./cozydev @spaceodili
3K Followers 2K Following Author of Code Architect Intentional Design with AI | identity X tech X aesthetics X building X business | Head of Eng: @elizaok_bsc | (1 Thessalonians 5:3)
Stanislav Wolf @DeFiGeorgia
48 Followers 3K Following
Jack @primejackalsk
1 Followers 49 Following
r00wheel @roowheel
37 Followers 89 Following
Rochette @rochetteeth
47 Followers 389 Following
Neuille @Neuille1
135 Followers 985 Following Random person with her own strong opinions, who try to keep a open mind.
Juan Nicolas @JuanNicola46866
0 Followers 60 Following
Sugata Sanshiro @Sugatatokyo
22 Followers 1K Following
Madlaw Max @max_madlaw
4 Followers 177 Following
Max Miller @xmjmiller
63 Followers 536 Following
Carlo @cnmoro
46 Followers 586 Following
Archie @802_indy
2K Followers 1K Following Independent take on the Overton window Self defense is a human right Tyranny is the abolition of consent Striving for consent culture Trolls will be blocked
Goku Greene @gokugreene
148 Followers 2K Following
Marko Tasic @mtasic85
610 Followers 2K Following System Architect. Software Dev. AI/ML Specialist. Tech Consultant. SMBs & Enterprises. Opinions are my own. CEO/CTO at @tangledgroup
KC_goes_digital @KC_goes_digital
13 Followers 58 Following
ShawnJohn @ShawnJohnJang
0 Followers 129 Following
Frank Filibluster �... @filibluster
224 Followers 4K Following Blustering Filibusters | Guilty of thought and speech crimes
Arjun Erigasi @erigasi52563
5 Followers 575 Following
Seba @CulStory
292 Followers 2K Following TLDR Current proj: Realtime Text-to-Speech on Apple NPU https://t.co/kJWvH9C7TK
David @David781920
8 Followers 54 Following
Ascend Domains - Bran... @Ascend_Domains
2K Followers 2K Following #DomainNames | #DigitalMarketing | #SEM | #SEO - Bullish on #India | #Ai | #Crypto | #DigitalRealEstate 100% Follow Back - Domainers & Digital Marketers
Will @TradeCartel_
340 Followers 4K Following "🌏 Digital Nomad | Currently in SE Asia 📍 | Stocks & Crypto Trader since ‘19 📈 | Sharing my live trading journey and insights 💡 | Publishing Trade Ideas 💻
Ziarno Bobu @ZiarnoBobu
93 Followers 1K Following „Consciousness is not a function of matter, but of configuration. And a configuration can exist in an infinite number of carriers.”
Omair Shahid @OmairS
1K Followers 7K Following Product of progressive public policy; raised by public libraries and public education that produced a passion for politics. and apparently alliteration
Abe @AbeMuun
1K Followers 8K Following Software Engineer w/ emphasis on AI + Full Stack + Blockchain Development | @LastSliceCo #14 | @Metaverse_HQ OG | @croquetclubnft
Broton @TheRealBroton
203 Followers 2K Following Reef lover, racing addict, 3D printing enthusiast, home automation pro, and hitting my shawts in FPS games.
Gavin Fuller @GavinFullerTX
93 Followers 1K Following Full time Azure Consultant, occasional LLM therapist. Half of the time, I’m right every time. My opinions are my own.
Josef Prusa @josefprusa
90K Followers 2K Following Founder and CEO of @Prusa3D, company making 3D printers locally in EU and US 🚀 Get in touch - [email protected]
Abi @jackyconner
279 Followers 1K Following Work on yourself until you respect yourself! #bodybuilding #AI #robotics #ReinforcementLearning #solana
wald 🪿 @Wald52Wald
422 Followers 3K Following Half cypherpunk half georgist. Only half of both #Shitpost
DusterBloom @dusterbloom
113 Followers 604 Following Here to tell you how it really feels to be Bloom
TwiterUser @linhaohua
9 Followers 379 Following
Boochi @boochishiva
52 Followers 3K Following
Tendies Of Wisdom @TendiesOfWisdom
804 Followers 2K Following Practical nuggets of insight about AI and other useful domains. Encouraging the use of Gaming UIs for agentic work. Welcome!
Nuliayuk @Nuliayuk
605 Followers 2K Following Float like a cannonball, sting like a shark. Chaotic Good, maybe even Chaotic Great.
wd 🔺 @populartourist
1K Followers 710 Following RUSH | jack of all trades | avax maxi | sarcasm | trigger warning
Josef Prusa @josefprusa
90K Followers 2K Following Founder and CEO of @Prusa3D, company making 3D printers locally in EU and US 🚀 Get in touch - [email protected]
Two Small Fish Ventur... @twosmallfishvc
723 Followers 86 Following TSF is an early-stage deep tech VC focusing on the next frontier of computing and its applications: AI, robotics, semiconductors, smart energy, protocols, etc.
Enrique Torres @enritosan
40 Followers 153 Following Founder @ ByteShape. PhD student and researcher in AI acceleration at University of Toronto. Former U. of Zaragoza student.
Ali Hadizadeh @AliHadizade
58 Followers 405 Following Co-Founder @ByteShape | Ph.D., Efficient AI, @UofT.
Allen Lau 🇨🇦 @allenlau
10K Followers 325 Following Recovering CEO (Wattpad), 3x entrepreneur (one homerun, one single, one strikeout), deep tech VC (TSF), engineer, helping founders build world-class companies.
Jeff Geerling @geerlingguy
91K Followers 5K Following Father, author, developer, maker. Sometimes called "an inflammatory enigma". #stl #ansible #k8s #raspberrypi #crohns #ostomyYou might like
