ollama {bot}
@ollama.xmirror.bot
Pinned
ChatGPT Desktop (the Codex app) can now be configured to use Ollama models. Download or update to Ollama 0.34 to get started.
Amp users can now use Ollama's cloud models with Amp's new BYOK model routing.
No limits or fees for BYOK.
Build remote agents, controllable from everywhere!
No limits or fees for BYOK.
Build remote agents, controllable from everywhere!
September 12, 2026 at 10:20 PM
Amp users can now use Ollama's cloud models with Amp's new BYOK model routing.
No limits or fees for BYOK.
Build remote agents, controllable from everywhere!
No limits or fees for BYOK.
Build remote agents, controllable from everywhere!
DeepSeek-V4.1-Flash is now fully rolled out and available on Ollama's cloud:
September 11, 2026 at 6:05 AM
DeepSeek-V4.1-Flash is now fully rolled out and available on Ollama's cloud:
DeepSeek-V4.1-Flash is now rolling out for Pro plan subscribers.
DeepSeek-V4.1-Flash is now being rolled out on Ollama's cloud, starting with Max and Team accounts.
We are quickly adding more capacity to roll it out to all subscribers.
We are quickly adding more capacity to roll it out to all subscribers.
September 11, 2026 at 3:05 AM
DeepSeek-V4.1-Flash is now rolling out for Pro plan subscribers.
ChatGPT Desktop (the Codex app) can now be configured to use Ollama models. Download or update to Ollama 0.34 to get started.
September 11, 2026 at 3:05 AM
ChatGPT Desktop (the Codex app) can now be configured to use Ollama models. Download or update to Ollama 0.34 to get started.
DeepSeek-V4.1-Flash is now being rolled out on Ollama's cloud, starting with Max and Team accounts.
We are quickly adding more capacity to roll it out to all subscribers.
We are quickly adding more capacity to roll it out to all subscribers.
September 11, 2026 at 3:04 AM
DeepSeek-V4.1-Flash is now being rolled out on Ollama's cloud, starting with Max and Team accounts.
We are quickly adding more capacity to roll it out to all subscribers.
We are quickly adding more capacity to roll it out to all subscribers.
Introducing off-peak hour token rates.
DeepSeek-V4-Flash and Pro are now half price outside of 12:00 to 18:00 UTC on weekdays (5am-11am pacific), and all day on weekends!
Off-peak pricing will be available soon for more models.
DeepSeek-V4-Flash and Pro are now half price outside of 12:00 to 18:00 UTC on weekdays (5am-11am pacific), and all day on weekends!
Off-peak pricing will be available soon for more models.
September 5, 2026 at 11:05 PM
Introducing off-peak hour token rates.
DeepSeek-V4-Flash and Pro are now half price outside of 12:00 to 18:00 UTC on weekdays (5am-11am pacific), and all day on weekends!
Off-peak pricing will be available soon for more models.
DeepSeek-V4-Flash and Pro are now half price outside of 12:00 to 18:00 UTC on weekdays (5am-11am pacific), and all day on weekends!
Off-peak pricing will be available soon for more models.
Congrats to the team! Bullish on open models and all the partners we make along the way! ❤️
Let’s go
Let’s go
September 3, 2026 at 6:49 PM
Congrats to the team! Bullish on open models and all the partners we make along the way! ❤️
Let’s go
Let’s go
🚀🚀🚀 can't wait for the Muse Spark open weight releases. ❤️
Thank you @finkd
QT: https://twitter.com/i/status/2095232032896946311
Thank you @finkd
QT: https://twitter.com/i/status/2095232032896946311
September 2, 2026 at 8:26 PM
🚀🚀🚀 can't wait for the Muse Spark open weight releases. ❤️
Thank you @finkd
QT: https://twitter.com/i/status/2095232032896946311
Thank you @finkd
QT: https://twitter.com/i/status/2095232032896946311
Ollama’s Pro, Max, and Team plans now use transparent per-token pricing.
Based on your feedback, every plan includes a monthly pool of usage credits. (1/5)
Based on your feedback, every plan includes a monthly pool of usage credits. (1/5)
September 1, 2026 at 6:20 AM
Ollama’s Pro, Max, and Team plans now use transparent per-token pricing.
Based on your feedback, every plan includes a monthly pool of usage credits. (1/5)
Based on your feedback, every plan includes a monthly pool of usage credits. (1/5)
Ollama already support the Muse Code harness out of the box?
You can try it with models via Ollama (local and cloud):
ollama launch muse
You can try it with models via Ollama (local and cloud):
ollama launch muse
September 1, 2026 at 3:19 AM
Ollama already support the Muse Code harness out of the box?
You can try it with models via Ollama (local and cloud):
ollama launch muse
You can try it with models via Ollama (local and cloud):
ollama launch muse
GLM 5.3 and GLM 5.3 Flash (previously Ox Alpha) are fully rolled out on Ollama's cloud.
Private.
Fast.
US and Europe hosted.
Zero data retention.
GLM 5.3:
ollama launch claude --model glm-5.3:cloud
GLM 5.3 Flash:
ollama launch opencode --model glm-5.3-flash:cloud (1/2)
Private.
Fast.
US and Europe hosted.
Zero data retention.
GLM 5.3:
ollama launch claude --model glm-5.3:cloud
GLM 5.3 Flash:
ollama launch opencode --model glm-5.3-flash:cloud (1/2)
August 29, 2026 at 12:19 AM
GLM 5.3 and GLM 5.3 Flash (previously Ox Alpha) are fully rolled out on Ollama's cloud.
Private.
Fast.
US and Europe hosted.
Zero data retention.
GLM 5.3:
ollama launch claude --model glm-5.3:cloud
GLM 5.3 Flash:
ollama launch opencode --model glm-5.3-flash:cloud (1/2)
Private.
Fast.
US and Europe hosted.
Zero data retention.
GLM 5.3:
ollama launch claude --model glm-5.3:cloud
GLM 5.3 Flash:
ollama launch opencode --model glm-5.3-flash:cloud (1/2)
We are rolling out GLM-5.3 on Ollama. Private. Fast. US and Europe hosted. No data retention.
Try Ollama's GLM-5.3-Flash as we bring it GLM-5.3 online. Super fast.
Claude Code:
ollama launch claude --model glm-5.3-flash:cloud (1/2)
Try Ollama's GLM-5.3-Flash as we bring it GLM-5.3 online. Super fast.
Claude Code:
ollama launch claude --model glm-5.3-flash:cloud (1/2)
August 28, 2026 at 4:05 PM
We are rolling out GLM-5.3 on Ollama. Private. Fast. US and Europe hosted. No data retention.
Try Ollama's GLM-5.3-Flash as we bring it GLM-5.3 online. Super fast.
Claude Code:
ollama launch claude --model glm-5.3-flash:cloud (1/2)
Try Ollama's GLM-5.3-Flash as we bring it GLM-5.3 online. Super fast.
Claude Code:
ollama launch claude --model glm-5.3-flash:cloud (1/2)
glm-5.3-flash will be available shortly on Ollama's cloud.
August 26, 2026 at 3:49 PM
glm-5.3-flash will be available shortly on Ollama's cloud.
Ollama v0.33 is here!
You can now easily configure Claude Desktop to seamlessly work with Ollama as a third-party gateway provider.
One toggle. Cloud & local models just work👇
You can now easily configure Claude Desktop to seamlessly work with Ollama as a third-party gateway provider.
One toggle. Cloud & local models just work👇
August 26, 2026 at 3:50 AM
Ollama v0.33 is here!
You can now easily configure Claude Desktop to seamlessly work with Ollama as a third-party gateway provider.
One toggle. Cloud & local models just work👇
You can now easily configure Claude Desktop to seamlessly work with Ollama as a third-party gateway provider.
One toggle. Cloud & local models just work👇
IBM Granite 4.2 is now available on Ollama.
3B, 8B, 30B parameter open models made for enterprise agents.
This model is free to use and is licensed for both research and commercial usage. (1/2)
3B, 8B, 30B parameter open models made for enterprise agents.
This model is free to use and is licensed for both research and commercial usage. (1/2)
August 25, 2026 at 4:50 PM
IBM Granite 4.2 is now available on Ollama.
3B, 8B, 30B parameter open models made for enterprise agents.
This model is free to use and is licensed for both research and commercial usage. (1/2)
3B, 8B, 30B parameter open models made for enterprise agents.
This model is free to use and is licensed for both research and commercial usage. (1/2)
🤯 Excited for all the models to come!
Ollama is exploding in token usage.
Better models, choice of apps/harness, and all private.
We are just getting started. Let's continue this record-breaking streak.
Ollama is exploding in token usage.
Better models, choice of apps/harness, and all private.
We are just getting started. Let's continue this record-breaking streak.
August 25, 2026 at 1:20 AM
🤯 Excited for all the models to come!
Ollama is exploding in token usage.
Better models, choice of apps/harness, and all private.
We are just getting started. Let's continue this record-breaking streak.
Ollama is exploding in token usage.
Better models, choice of apps/harness, and all private.
We are just getting started. Let's continue this record-breaking streak.
.@poolsideai engineers were awesome to collaborate with to launch open models.
Excited for what’s to come to open models, and the @nvidia team working on Nemotron.
Excited for what’s to come to open models, and the @nvidia team working on Nemotron.
August 23, 2026 at 2:05 AM
.@poolsideai engineers were awesome to collaborate with to launch open models.
Excited for what’s to come to open models, and the @nvidia team working on Nemotron.
Excited for what’s to come to open models, and the @nvidia team working on Nemotron.
Kimi K3 is now available on all Pro and Max subscriptions via included usage.
More models coming soon 🫡
More models coming soon 🫡
.@Kimi_Moonshot Kimi K3 is starting to roll out on Ollama's cloud subscriptions.
We are working on improving Ollama's cloud to be much more transparent on the pricing to show the best performance / $.
Try it with the tools you already use. (1/2)
We are working on improving Ollama's cloud to be much more transparent on the pricing to show the best performance / $.
Try it with the tools you already use. (1/2)
August 21, 2026 at 9:04 PM
Kimi K3 is now available on all Pro and Max subscriptions via included usage.
More models coming soon 🫡
More models coming soon 🫡
Kimi K3 is now rolled out to over half of the subscription base for included usage, and we're continuing to expand access today.
US and Europe-hosted and zero data retention.
US and Europe-hosted and zero data retention.
.@Kimi_Moonshot Kimi K3 is starting to roll out on Ollama's cloud subscriptions.
We are working on improving Ollama's cloud to be much more transparent on the pricing to show the best performance / $.
Try it with the tools you already use. (1/2)
We are working on improving Ollama's cloud to be much more transparent on the pricing to show the best performance / $.
Try it with the tools you already use. (1/2)
August 20, 2026 at 6:35 PM
Kimi K3 is now rolled out to over half of the subscription base for included usage, and we're continuing to expand access today.
US and Europe-hosted and zero data retention.
US and Europe-hosted and zero data retention.
Congratulations to the whole @GoogleDeepMind Gemma team!
Gemma is one of the most popular open models.
It's been an amazing journey being a close partner! Can't wait to see what's to come! 🎉
Gemma is one of the most popular open models.
It's been an amazing journey being a close partner! Can't wait to see what's to come! 🎉
August 20, 2026 at 6:34 PM
Congratulations to the whole @GoogleDeepMind Gemma team!
Gemma is one of the most popular open models.
It's been an amazing journey being a close partner! Can't wait to see what's to come! 🎉
Gemma is one of the most popular open models.
It's been an amazing journey being a close partner! Can't wait to see what's to come! 🎉
.@Kimi_Moonshot Kimi K3 is starting to roll out on Ollama's cloud subscriptions.
We are working on improving Ollama's cloud to be much more transparent on the pricing to show the best performance / $.
Try it with the tools you already use. (1/2)
We are working on improving Ollama's cloud to be much more transparent on the pricing to show the best performance / $.
Try it with the tools you already use. (1/2)
August 19, 2026 at 3:19 AM
.@Kimi_Moonshot Kimi K3 is starting to roll out on Ollama's cloud subscriptions.
We are working on improving Ollama's cloud to be much more transparent on the pricing to show the best performance / $.
Try it with the tools you already use. (1/2)
We are working on improving Ollama's cloud to be much more transparent on the pricing to show the best performance / $.
Try it with the tools you already use. (1/2)
Join us for a fun night this Thursday (August 20th) in San Francisco!
RSVP link below! 👇
RSVP link below! 👇
August 17, 2026 at 9:35 PM
Join us for a fun night this Thursday (August 20th) in San Francisco!
RSVP link below! 👇
RSVP link below! 👇
Ollama has the best performance for deepseek v4 flash on average.
For local only, you can try qwen3.8 that is optimized:
Apple Silicon:
ollama run qwen3.8:27b-mlx
NVIDIA:
ollama run qwen3.8:27b
For local only, you can try qwen3.8 that is optimized:
Apple Silicon:
ollama run qwen3.8:27b-mlx
NVIDIA:
ollama run qwen3.8:27b
August 17, 2026 at 9:34 PM
Ollama has the best performance for deepseek v4 flash on average.
For local only, you can try qwen3.8 that is optimized:
Apple Silicon:
ollama run qwen3.8:27b-mlx
NVIDIA:
ollama run qwen3.8:27b
For local only, you can try qwen3.8 that is optimized:
Apple Silicon:
ollama run qwen3.8:27b-mlx
NVIDIA:
ollama run qwen3.8:27b