ollama(@ollama)

Open models are improving at an unprecedented rate. Congrats to the whole @Zai_org team. Ollama ...

ollama (@ollama) — Fri, 14 Aug 2026 06:37:30 GMT

Open models are improving at an unprecedented rate. 

Congrats to the whole @Zai_org team. 

Ollama will support GLM-5.3 upon the open release! ❤️

Get ready to code.

Z.ai@Zai_org

Introducing GLM-5.3: Built to Code. Ready for Cyber Defense.

- Top-tier coding and agentic capabilities, achieved through post-training on the 743B base model
- A major leap in cybersecurity, setting a new standard among open models

Tech Blog: z.ai/blog/glm-5.3

💬47🔄44❤️984👀43309📊107

Using @AIatMeta's Muse Glimmer all locally to process personal monthly credit card statements. You...

ollama (@ollama) — Thu, 13 Aug 2026 18:10:57 GMT

Using @AIatMeta's Muse Glimmer all locally to process personal monthly credit card statements. 

Your data belongs to you! 

Try different agent tasks using your favorite apps / harnesses with Ollama.

Your browser does not support the video tag.

💬12🔄26❤️303👀25456📊52

Model page: https://t.co/0bPXJUf2rO

ollama (@ollama) — Thu, 13 Aug 2026 18:10:57 GMT

Model page: 
ollama.com/library/muse-g…

💬0🔄1❤️8👀3566📊1

You can now use Ollama as a provider in GitHub Copilot for JetBrains. https://t.co/Rt8iSMYWaA

ollama (@ollama) — Wed, 12 Aug 2026 01:35:35 GMT

You can now use Ollama as a provider in GitHub Copilot for JetBrains. 

github.blog/changelog/2026…

💬18🔄18❤️194👀16937📊40

It's been exciting for Ollama to partner with @JensenHuang and the @NVIDIAAI team on launching open ...

ollama (@ollama) — Tue, 11 Aug 2026 18:07:25 GMT

It's been exciting for Ollama to partner with @JensenHuang and the @NVIDIAAI team on launching open models. 

Open models have no boundaries, and let's continue to work together to make this ecosystem better!

Jensen Huang@JensenHuang

Lightning strikes for continuous and long-run agents!

Nemotron 3.5 Lightning is smart, fast, efficient and open.

💬14🔄38❤️586👀42266📊61

blog post https://t.co/oz75j8oQQE

ollama (@ollama) — Tue, 11 Aug 2026 16:03:22 GMT

blog post 

ollama.com/blog/nemotron-…

💬2🔄1❤️12👀4180📊3

https://t.co/3m4pdSkkFx

ollama (@ollama) — Tue, 11 Aug 2026 16:02:22 GMT

ollama.com/library/nemotr…

💬1🔄1❤️13👀4663📊3

NVIDIA Nemotron 3.5 Lighting is available on Ollama! It's a 30B model made for always-on agents. A...

ollama (@ollama) — Tue, 11 Aug 2026 16:02:21 GMT

NVIDIA Nemotron 3.5 Lighting is available on Ollama! 

It's a 30B model made for always-on agents. All local. 

Claude Code 
ollama launch claude --model nemotron-3.5-lightning

Hermes Agent
ollama launch hermes --model nemotron-3.5-lightning

OpenClaw
ollama launch openclaw --model nemotron-3.5-lightning

- 30B mixture of experts model with 3B active
- 1M token context
- built for agents that stay running: coding, tool calling, multi-turn
- 4x higher throughput and 30% lower task completion time compared to other leading open models of similar size

Model page
👇👇👇

NVIDIA AI@NVIDIAAI

Introducing NVIDIA Nemotron 3.5 Lightning⚡

An open 30B MoE model with 3B active parameters, built for always-on agents to complete high-volume, specialized tasks faster.

It delivers up to 4x the output speed of similar-sized models.

💬43🔄77❤️791👀75442📊120

Blog post: https://t.co/7Qs53yG2to

ollama (@ollama) — Mon, 10 Aug 2026 11:49:13 GMT

Blog post: ollama.com/blog/muse-glim…

💬6🔄0❤️29👀7201📊9

Muse Glimmer is now available to run with Ollama. Available today via Ollama’s MLX engine with stat...

ollama (@ollama) — Mon, 10 Aug 2026 11:49:01 GMT

Muse Glimmer is now available to run with Ollama.

Available today via Ollama’s MLX engine with state-of-the-art-performance on Apple Silicon, Muse Glimmer can power Claude Code, Codex, and more always-on local agent workflows natively using Ollama.

Additional support and optimizations for Apple Silicon, NVIDIA, AMD, and other platforms will be available shortly.

Go @finkd@alexandr_wang and @Meta !

Mark Zuckerberg@finkd

Today we're also opening the weights for Muse Glimmer, a great 30B parameter dense model that can run locally. Soon we'll also release the weights for Muse Spark 1.2, our latest foundation model. Meta is a strong supporter of open source and I'm proud of these releases. Congrats to @alexandr_wang and the MSL team for all your great work on these models.

💬67🔄110❤️1351👀91401📊182

Currently serving 200 tps+ output speed for DeepSeek-V4-Flash on Ollama's cloud with zero data reten...

ollama (@ollama) — Sat, 08 Aug 2026 06:24:31 GMT

Currently serving 200 tps+ output speed for DeepSeek-V4-Flash on Ollama's cloud with zero data retention (ZDR).

Have an amazing weekend 🫡

ollama@ollama

DeepSeek-V4-Flash-0731 is now fully rolled out as the new default for deepseek-v4-flash on Ollama's cloud.

This model combines speed, efficiency, and frontier-level performance.

Fast: 120+ output tps on Ollama's cloud
Private: zero data retention hosting in US & Europe
Efficient: generous usage on Ollama's Pro and Max plans for multiple long-running, uninterrupted sessions with your favorite coding harnesses.

💬99🔄93❤️2072👀187690📊261

Model page: https://t.co/Z4u6ruZJhg

ollama (@ollama) — Fri, 07 Aug 2026 19:55:06 GMT

Model page: ollama.com/library/deepse…

💬3🔄3❤️39👀16816📊8

DeepSeek-V4-Flash-0731 is now fully rolled out as the new default for deepseek-v4-flash on Ollama's ...

ollama (@ollama) — Fri, 07 Aug 2026 19:54:53 GMT

DeepSeek-V4-Flash-0731 is now fully rolled out as the new default for deepseek-v4-flash on Ollama's cloud.

This model combines speed, efficiency, and frontier-level performance.

Fast: 120+ output tps on Ollama's cloud
Private: zero data retention hosting in US & Europe
Efficient: generous usage on Ollama's Pro and Max plans for multiple long-running, uninterrupted sessions with your favorite coding harnesses.

💬66🔄87❤️1952👀334652📊279

Model page: https://t.co/0AvMN39sZZ

ollama (@ollama) — Tue, 04 Aug 2026 22:42:02 GMT

Model page: ollama.com/library/deepse…

💬2🔄1❤️57👀28434📊9

DeepSeek-V4-Flash-0731 is Ollama's fastest growing model ever in token usage. We are scaling capacit...

ollama (@ollama) — Tue, 04 Aug 2026 22:41:45 GMT

DeepSeek-V4-Flash-0731 is Ollama's fastest growing model ever in token usage. We are scaling capacity in US & Europe.

On Ollama, this model runs with high performance (100tps+) and zero data retention. Your data stays yours.

ollama run deepseek-v4-flash:0731-cloud

💬146🔄285❤️5611👀387011📊819

DeepSeek-V4-Flash-0731 is now over 2x faster than yesterday on Ollama's cloud!

ollama (@ollama) — Sat, 01 Aug 2026 22:47:59 GMT

DeepSeek-V4-Flash-0731 is now over 2x faster than yesterday on Ollama's cloud!

ollama@ollama

DeepSeek-V4-Flash-0731 is now available on Ollama's cloud. This update substantially enhances the model's agentic capabilities:

ollama run deepseek-v4-flash:0731-cloud

Use it with Claude Code:

ollama launch claude --model deepseek-v4-flash:0731-cloud

💬96🔄103❤️2355👀194220📊259

DeepSeek-V4-Flash-0731 is now available on Ollama's cloud. This update substantially enhances the mo...

ollama (@ollama) — Sat, 01 Aug 2026 04:34:38 GMT

DeepSeek-V4-Flash-0731 is now available on Ollama's cloud. This update substantially enhances the model's agentic capabilities:

ollama run deepseek-v4-flash:0731-cloud

Use it with Claude Code:

ollama launch claude --model deepseek-v4-flash:0731-cloud

💬92🔄132❤️1978👀332979📊327

Excited to work with the @IntelBusiness team on enabling open models with Intel Core Ultra Series 3.

ollama (@ollama) — Thu, 30 Jul 2026 05:42:09 GMT

Excited to work with the @IntelBusiness team on enabling open models with Intel Core Ultra Series 3.

Intel Business@IntelBusiness

Built to bring open-source LLMs to private machines, @Ollama uses Intel Core Ultra Series 3 to run local inferencing tailored to your workflow.

Learn more: ms.spr.ly/6017vhXhN

💬30🔄16❤️245👀33928📊40

Model page: https://t.co/DXMhMhBpCk

ollama (@ollama) — Mon, 27 Jul 2026 15:58:30 GMT

Model page: ollama.com/library/kimi-k3

💬16🔄4❤️55👀16928📊20

Kimi K3 is now available on Ollama’s cloud. To use it with Claude Code, run: ollama launch claude ...

ollama (@ollama) — Mon, 27 Jul 2026 15:58:07 GMT

Kimi K3 is now available on Ollama’s cloud.

To use it with Claude Code, run:

ollama launch claude --model kimi-k3:cloud

Currently Kimi K3 requires a Pro or Max subscription, and consumes extra usage credits. We’re quickly working on adding capacity to expand access.

Kimi.ai@Kimi_Moonshot

Releasing the model weights and technical report of Kimi K3.

Kimi K3 is our most capable model: a 2.8T MoE model with native visual understanding and a 1M-token context window.

New model architecture: 2.5x the intelligence per unit of compute, not just more params.

Alongside Kimi K3, we're opening up more of the stack behind it — high-performance attention kernels, MoE communication library, and infrastructure for running agent environments at scale.

Model weights: huggingface.co/moonshotai/Kim…
Tech report:  github.com/MoonshotAI/Kim…
Tech blog: kimi.com/blog/kimi-k3

💬245🔄328❤️3368👀329217📊556

Ollama is proud to sign @satyanadella's letter. Our mission from day one has been to make open mode...

ollama (@ollama) — Sun, 26 Jul 2026 00:45:43 GMT

Ollama is proud to sign @satyanadella's letter.

Our mission from day one has been to make open models accessible to every developer to unlock the next frontier in America and across the globe.

Satya Nadella@satyanadella

Open-weight models are essential to a healthy AI ecosystem. Together with others across our industry, we are outlining a path for open-weight models to strengthen American competitiveness and expand economic opportunity, while protecting national security. microsoft.com/en-us/corporat…

💬76🔄219❤️3614👀227795📊361

Open 24/7!

ollama (@ollama) — Sun, 26 Jul 2026 00:23:18 GMT

Open 24/7!

Denny’s@DennysDiner

@JensenHuang@nvidia

💬18🔄35❤️844👀42116📊76

The demand for GLM-5.2 and other frontier-level open models has been surging on Ollama's cloud. We'...

ollama (@ollama) — Fri, 24 Jul 2026 20:04:54 GMT

The demand for GLM-5.2 and other frontier-level open models has been surging on Ollama's cloud.

We're adding capacity in anticipation for some very large models next week! To make sure Ollama's infrastructure stays fast we're temporarily pausing new subscriptions on Ollama's Max plan.

Existing Max subscribers are not affected and Ollama's Pro plan is still available to subscribe to.

💬81🔄79❤️1829👀217950📊266

Open models matter. Ollama works hard with the model creators, hardware partners, and most import...

ollama (@ollama) — Fri, 24 Jul 2026 15:33:54 GMT

Open models matter. 

Ollama works hard with the model creators,  hardware partners, and most importantly developers building software leveraging various open models for their own use cases.

Jensen Huang@JensenHuang

For my first post, I’m sharing a letter @NVIDIA signed on why open models matter.

AI will transform every industry, power every company, and be built by every country.

Open models strengthen safety and cybersecurity, accelerate innovation and diffusion, and enable sovereignty.

The world needs both frontier closed models and frontier open models.

images.nvidia.com/pdf/Open-Weigh…

💬69🔄258❤️3181👀112675📊325

Ollama's @jmorgan joined Yahoo Finance to talk about why Fortune 500 companies are shifting to open-...

ollama (@ollama) — Thu, 23 Jul 2026 03:25:39 GMT

Ollama's @jmorgan joined Yahoo Finance to talk about why Fortune 500 companies are shifting to open-source models for lower costs and more control over their data.

Watch the full interview: ca.finance.yahoo.com/video/why-fort…

💬10🔄17❤️120👀18211📊27

Ollama 0.32.1 includes significant improvements to Gemma 4's tool calling, making it much more relia...

ollama (@ollama) — Fri, 17 Jul 2026 18:24:19 GMT

Ollama 0.32.1 includes significant improvements to Gemma 4's tool calling, making it much more reliable in coding agents!

To try Gemma 4 26B with Pi, run:

ollama launch pi --model gemma4:26b

With Ollama's MLX engine for maximum performance, run:

ollama launch pi --model gemma4:26b-mlx

Google Gemma@googlegemma

We’re rolling out some big improvements to Gemma 4, fueled by incredible community feedback and contributions! 

Here is a breakdown of what’s being fixed and updated in this release: 🧵👇

💬47🔄99❤️849👀99146📊145

Open models are already being used in the enterprise. Over 85% of the Fortune 500 companies alread...

ollama (@ollama) — Thu, 16 Jul 2026 02:11:18 GMT

Open models are already being used in the enterprise. 

Over 85% of the Fortune 500 companies already use Ollama to fulfill specific tasks. @jmorgan 

Why open models and Ollama? 

Ownership. 

Open models are yours to keep, customize, and optimize. 

Affordable. 

Run it the way you like, in your own environment. 

Private. 

Your data belongs to you.

Your browser does not support the video tag.

💬33🔄56❤️448👀42774📊91

Ollama is back in NYC today! It's exciting to see more people and businesses realize the benefits ...

ollama (@ollama) — Wed, 15 Jul 2026 04:21:36 GMT

Ollama is back in NYC today! 

It's exciting to see more people and businesses realize the benefits of open models! Ownership. Affordable. Private. 

Thank you @Nasdaq and the @Theoryvc team.

💬30🔄39❤️507👀28493📊79

You can use OpenCode Desktop with Ollama! Try it with the top open models!

ollama (@ollama) — Wed, 15 Jul 2026 00:33:43 GMT

You can use OpenCode Desktop with Ollama!

Try it with the top open models!

OpenCode@opencode

Introducing Tabs

OpenCode Desktop is now built around tabs.

Start a new session in a tab, or open an existing session from any of your projects.

Open a new tab when you're starting something new, and close it when you're done.

Download the latest to get started.

Your browser does not support the video tag.

💬28🔄94❤️1091👀115177📊154

https://t.co/OFMadOyafl https://t.co/uN1EUzLKNm

ollama (@ollama) — Wed, 15 Jul 2026 00:33:43 GMT

docs.ollama.com/integrations/o…opencode.ai/docs/providers…

💬0🔄3❤️17👀6661📊3

U.S. open-source models are quickly gaining ground. @Nvidia's newest Nemotron Ultra is fast growin...

ollama (@ollama) — Tue, 14 Jul 2026 00:01:12 GMT

U.S. open-source models are quickly gaining ground. 

@Nvidia's newest Nemotron Ultra is fast growing on Ollama and unlocking complex, longer running tasks for developers

Your browser does not support the video tag.

💬22🔄38❤️426👀73349📊75

Ollama's @jmorgan is live on Yahoo Finance to talk about open models. https://t.co/5lbJeMHf1L

ollama (@ollama) — Mon, 13 Jul 2026 20:30:45 GMT

Ollama's @jmorgan is live on Yahoo Finance to talk about open models. 

finance.yahoo.com/live/

💬10🔄6❤️113👀18004📊20

@jmorgan was on @tbpn this week to discuss Ollama's Series B fundraise and why open models are quick...

ollama (@ollama) — Sun, 12 Jul 2026 03:33:33 GMT

@jmorgan was on @tbpn this week to discuss Ollama's Series B fundraise and why open models are quickly becoming the default choice for developers

Full video:

Your browser does not support the video tag.

💬7🔄12❤️120👀36522📊22

Token usage beginning to tip towards open models. Ollama’s @jmorgan and Peter Fenton predict that ...

ollama (@ollama) — Fri, 10 Jul 2026 20:56:44 GMT

Token usage beginning to tip towards open models. 

Ollama’s @jmorgan and Peter Fenton predict that a supermajority of tokens in the future will be from open models.

Deirdre Bosa@dee_bosa

Is compute scarcity masking the real economics of AI?

interesting point from @peterfenton: open-weight models are still complex to run well. For now, the big labs have the bundle: model + compute + reliability + access... and thus pricing power.

But if compute supply loosens and open model tooling gets easier, routine AI work can more easily move to cheaper/open models.

Your browser does not support the video tag.

💬24🔄30❤️265👀33689📊43

@jmorgan @peterfenton @CNBC @dee_bosa livestream link: https://t.co/TmQeAKv0sy

ollama (@ollama) — Thu, 09 Jul 2026 18:31:38 GMT

@jmorgan@peterfenton@CNBC@dee_bosa livestream link: 
youtube.com/watch?v=gppIDG…

💬0🔄1❤️11👀7834📊2

Watch Ollama's @jmorgan and @peterfenton on @CNBC with @dee_bosa at 12pm PT / 3pm ET to discuss "Th...

ollama (@ollama) — Thu, 09 Jul 2026 18:31:11 GMT

Watch Ollama's @jmorgan and @peterfenton on @CNBC  with @dee_bosa at 12pm PT / 3pm ET to discuss "The Post-Frontier Era" and "Open-Source AI's Breakout Moment"

Deirdre Bosa@dee_bosa

Benchmark’s @peterfenton says 90%+ of tokens could  come from open weight models in the next 18-24 months, pressuring frontier model margins.

Full convo at 12p PT/3p ET on the livestream, plus @AravSrinivas on Perplexity’s new orchestrator model and @jmorgan on why enterprises are moving toward AI models they can download and control

Your browser does not support the video tag.

💬9🔄5❤️69👀16699📊12

.@jmorgan will be live on TBPN today.

ollama (@ollama) — Thu, 09 Jul 2026 18:12:58 GMT

.@jmorgan will be live on TBPN today.

TBPN@tbpn

Happy Thursday. On today's show:

- @thsottiaux (OpenAI)
- @eric_seufert (Mobile Dev Memo)
- @Seanfrank (Ridge)
- @BerntBornich (1X)
- @jmorgan (Ollama)
- Josh Lindgren (CAA)

See you on the stream.

💬6🔄3❤️54👀15461📊8

https://t.co/8UoPBJmDiX

ollama (@ollama) — Thu, 09 Jul 2026 13:31:13 GMT

ollama.com/blog/all-aboar…

💬4🔄5❤️107👀15564📊17

Big day for Ollama! When we started, open models and the open source AI ecosystem were in their earl...

ollama (@ollama) — Thu, 09 Jul 2026 13:31:12 GMT

Big day for Ollama! When we started, open models and the open source AI ecosystem were in their early days with few believers.

Our belief in open source has never wavered.

With today's fundraising announcement and our 9M+ active builders, we’re ready to scale open models into AI that you can own.

All aboard open models!

🧵

💬210🔄238❤️2049👀333050📊459

See you tomorrow!

ollama (@ollama) — Thu, 09 Jul 2026 04:11:09 GMT

See you tomorrow!

💬54🔄26❤️824👀50714📊125

Model page: https://t.co/XAyHmEPGOr

ollama (@ollama) — Wed, 08 Jul 2026 02:06:30 GMT

Model page: 
ollama.com/library/glm-5.2

💬2🔄0❤️28👀7747📊5

GLM-5.2 on Ollama's cloud just got more capacity in US & Europe! Ollama's cloud for GLM 5.2 consis...

ollama (@ollama) — Wed, 08 Jul 2026 02:06:29 GMT

GLM-5.2 on Ollama's cloud just got more capacity in US & Europe! 

Ollama's cloud for GLM 5.2 consistently delivers between 80 to 120 output tokens per second, even during peak hours, compared to 30 to 40 tok/s on other providers. 

Use GLM-5.2 with

Claude Code: 
ollama launch claude

VS Code
ollama launch vscode

Codex
ollama launch codex

Hermes
ollama launch hermes

💬51🔄44❤️782👀65395📊137

Congratulations to our friends at @togethercompute. Exciting moment for open models!!

ollama (@ollama) — Wed, 01 Jul 2026 19:46:20 GMT

Congratulations to our friends at @togethercompute. Exciting moment for open models!!

Vipul Ved Prakash@vipulved

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! 

shorturl.at/SooOP

💬5🔄8❤️174👀28560📊19

Gemma 4 is now nearly 90% faster on Apple Silicon with Ollama using MLX! The speedup comes from imp...

ollama (@ollama) — Wed, 01 Jul 2026 00:54:17 GMT

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.

💬66🔄266❤️3399👀210178📊616

Model page: https://t.co/xbTqD7KPEt

ollama (@ollama) — Sat, 27 Jun 2026 20:47:11 GMT

Model page: ollama.com/library/ornith

💬2🔄1❤️31👀8299📊6

Run Ornith with Ollama: ollama run ornith For coding, use it with Claude or Pi: ollama launch cla...

ollama (@ollama) — Sat, 27 Jun 2026 20:46:51 GMT

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

Ornith@ornith_

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 coding benchmarks including:
✅Terminal-Bench 2.1(77.5)
✅SWE-Bench(82.4 on verified, 62.2 on pro, 78.9 on Multilingual)
✅NL2Repo(48.2)
✅SWE Atlas(41.2 on QnA, 42.6 RF, 39.1 TW)
✅ClawEval(77.1)

Post-trained on top of gemma4 and qwen3.5, Ornith-1.0 employs a novel self-improving training strategy in which reinforcement learning is used to generate not only solution rollouts, but also the task-specific scaffolds that drive those rollouts. By jointly optimizing the scaffold and the resulting solution, the model  generate higher-quality solutions in agentic coding.😎

All models are released under the MIT license, enabling full commercial and research use.

📖Tech Blodeep-reinforce.com/ornith_1_0.htmlWFn
🤗Huggingfahuggingface.co/collections/de…eBtM

💬51🔄118❤️1332👀137529📊228

Let’s go open models! ❤️

ollama (@ollama) — Sun, 21 Jun 2026 02:47:08 GMT

Let’s go open models! ❤️

Guillermo Rauch@rauchg

Genuinely impressed, almost shocked, at how good GLM-5.2 by @zai_org is at coding. This changes things.

💬33🔄52❤️1119👀80725📊111

Let’s go open models! ❤️

ollama (@ollama) — Sat, 20 Jun 2026 21:07:14 GMT

Let’s go open models! ❤️

Aaron Levie@levie

Pretty remarkable what’s happening with open weights AI right now. We’re seeing models achieve SOTA results on specific tasks, and getting close to frontier on some areas of coding and other domains. 

The more that open weights is able to maintain only a marginal gap from the frontier, instead of a widening gap, the more value that can be created with AI.

Incidentally, this is actually fine for the frontier labs as well; if we can lower the cost of an overall task then AI usage goes up in general. You’re still likely using frontier models for planning, orchestration, reviewing, and other parts of work. 

But this is all very good for the applied layer of AI, which is now in a great position to cost optimize workloads with cheaper models or use tailored open models post-trained for specific tasks to improve performance.