We @togethercompute believe intelligence should be abundant, not expensive.
Today we announced our Series C funding of $800m @ $8.3B valuation, to continue to build the world's most efficient platform for generative AI.
Thanks @nikogallogly for telling our story in @nytimes!
Gemma 4 is now nearly 90% faster on Apple Silicon with Ollama using MLX!
The speedup comes from improved multi-token prediction (MTP), now on by default for Gemma 4, with more models to come.
Ollama automatically tunes how many tokens to draft as it runs, so it never slows generation down when speculation no longer contributes to a speedup.
Run Ornith with Ollama:
ollama run ornith
For coding, use it with Claude or Pi:
ollama launch claude --model ornith
ollama launch pi --model ornith
For the more capable 35B model, use:
ollama launch claude --model ornith:35b
Aloha! 🌺 Meet Ornith-1.0, a family of open-source LLMs specialized for agentic coding.
Ornith-1.0 spans the full parameter sizes including 9B Dense, 31B Dense, 35B MoE, and 397B MoE. It achieves state-of-the-art performance among open-source models of comparable size on
Deepswe's benchmark results are my own experience.
I've used all models,
GLM 5.2 ≈ Claude Opus 4.6–4.7.
Kimi 2.7 code more like inference optimization.
Looking forward to K3.
Doubao-seed 2.1 Pro around 37% ≈ Gemini 3.5 Flash.
code are quite weak, but visual are strong.
At @aiDotEngineer World's Fair next week? Come join us Tuesday night 🏓
We're co-hosting an evening at SPIN with @TheoryVC and @ollama. Talk shop with the people building the next-generation of local and cloud AI infrastructure, grab a drink, and get a few games in.
📅 Tuesday, June 30 @ 6:00 PM
📍 SPIN San Francisco
🎟️ Space is limited: lu.ma/localserve
BYOK is now live in the GitHub Copilot App!
Works with @ollama, foundry, and any OAI completions or Anthropic compatible messages endpoint. Give it a try today!
The sharpest questions in AI live at the local–cloud boundary : where should inference run, & where should your data live?
In town for AIE? Come hash it out with @Theoryvc, @lancedb & @ollama.
June 30 · 6–9PM · SPIN SF 🏓 luma.com/localserve
@Dev4YM@rubenssoto_ai So sorry to hear you’re having problems. May I ask which model and when it happened? Is it still happening now?
We’ve been adding more capacity.
21 Followers 20 FollowingMaking Oddvark — a 100% local AI assistant. Chat, voice, screen vision & PC control. Open source, no cloud, no API keys. Discord: https://t.co/2LsmYqmYv7
158 Followers 543 FollowingLibertarianism. Realpolitik. Good tradeoffs, not solutions. The art of the possible. WMC fat cat. Connoisseur of leftie and commie tears.
Pronouns: Ho/hum
10K Followers 785 FollowingEspecialista en adopción empresarial de IA y Automatización. Foco en Productividad, Optimización, Marketing y Ventas. Estrategias IA-first
70 Followers 290 FollowingJag är egentligen för gammal för sånt här men jag kan inte vara sämre än min dotter. :-) Funderingar om bandy, it-säkerhet och försvar på Svenska och Finska.
1.3M Followers 176 FollowingNobel Laureate. Co-Founder & CEO @GoogleDeepMind - working on AGI. Solving disease @IsomorphicLabs. Trying to understand the fundamental nature of reality.