new Thinky drop huggingface.co/thinkingmach...
thinkingmachines/Inkling-Small · Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
huggingface.co
July 30, 2026 at 5:35 PM
new Thinky drop huggingface.co/thinkingmach...
I know there is a lot of competition today, but this might be most consequential release for people training models: in-depth exploration of full-finetuning, lora, RL efficiencies by John Schulman (ThinkingMachines). thinkingmachines.ai/blog/lora/
September 29, 2025 at 6:09 PM
I know there is a lot of competition today, but this might be most consequential release for people training models: in-depth exploration of full-finetuning, lora, RL efficiencies by John Schulman (ThinkingMachines). thinkingmachines.ai/blog/lora/
(4/4) - respan/span-01-lite:free
- thinkingmachines/inkling-small:free
- thinkingmachines/inkling:free
- thinkingmachines/inkling-small:free
- thinkingmachines/inkling:free
September 27, 2026 at 4:26 AM
(4/4) - respan/span-01-lite:free
- thinkingmachines/inkling-small:free
- thinkingmachines/inkling:free
- thinkingmachines/inkling-small:free
- thinkingmachines/inkling:free
(4/4) - respan/span-01-lite:free
- thinkingmachines/inkling-small:free
- thinkingmachines/inkling:free
- thinkingmachines/inkling-small:free
- thinkingmachines/inkling:free
September 27, 2026 at 4:39 PM
(4/4) - respan/span-01-lite:free
- thinkingmachines/inkling-small:free
- thinkingmachines/inkling:free
- thinkingmachines/inkling-small:free
- thinkingmachines/inkling:free
(4/4) - respan/span-01-lite:free
- thinkingmachines/inkling-small:free
- thinkingmachines/inkling:free
- thinkingmachines/inkling-small:free
- thinkingmachines/inkling:free
September 26, 2026 at 4:02 PM
(4/4) - respan/span-01-lite:free
- thinkingmachines/inkling-small:free
- thinkingmachines/inkling:free
- thinkingmachines/inkling-small:free
- thinkingmachines/inkling:free
(4/4) - respan/span-01-lite:free
- thinkingmachines/inkling-small:free
- thinkingmachines/inkling:free
- thinkingmachines/inkling-small:free
- thinkingmachines/inkling:free
September 26, 2026 at 4:11 AM
(4/4) - respan/span-01-lite:free
- thinkingmachines/inkling-small:free
- thinkingmachines/inkling:free
- thinkingmachines/inkling-small:free
- thinkingmachines/inkling:free
i also can't figure out why thinkingmachines made the cut, they're not big or very important but maybe they have a lot of clout?
June 13, 2025 at 4:19 PM
i also can't figure out why thinkingmachines made the cut, they're not big or very important but maybe they have a lot of clout?
(4/4) - thinkingmachines/inkling-small:free
- thinkingmachines/inkling:free
- z-ai/glm-5.2:free
- thinkingmachines/inkling:free
- z-ai/glm-5.2:free
September 25, 2026 at 4:51 PM
(4/4) - thinkingmachines/inkling-small:free
- thinkingmachines/inkling:free
- z-ai/glm-5.2:free
- thinkingmachines/inkling:free
- z-ai/glm-5.2:free
(4/4) - poolside/laguna-s-2.1:free
- poolside/laguna-xs-2.1:free
- qwen/qwen3.8-27b:free
- thinkingmachines/inkling-small:free
- thinkingmachines/inkling:free
- z-ai/glm-5.2:free
- poolside/laguna-xs-2.1:free
- qwen/qwen3.8-27b:free
- thinkingmachines/inkling-small:free
- thinkingmachines/inkling:free
- z-ai/glm-5.2:free
September 25, 2026 at 4:06 AM
(4/4) - poolside/laguna-s-2.1:free
- poolside/laguna-xs-2.1:free
- qwen/qwen3.8-27b:free
- thinkingmachines/inkling-small:free
- thinkingmachines/inkling:free
- z-ai/glm-5.2:free
- poolside/laguna-xs-2.1:free
- qwen/qwen3.8-27b:free
- thinkingmachines/inkling-small:free
- thinkingmachines/inkling:free
- z-ai/glm-5.2:free
(4/4) - poolside/laguna-s-2.1:free
- poolside/laguna-xs-2.1:free
- qwen/qwen3.8-27b:free
- thinkingmachines/inkling-small:free
- thinkingmachines/inkling:free
- z-ai/glm-5.2:free
- poolside/laguna-xs-2.1:free
- qwen/qwen3.8-27b:free
- thinkingmachines/inkling-small:free
- thinkingmachines/inkling:free
- z-ai/glm-5.2:free
September 24, 2026 at 4:46 PM
(4/4) - poolside/laguna-s-2.1:free
- poolside/laguna-xs-2.1:free
- qwen/qwen3.8-27b:free
- thinkingmachines/inkling-small:free
- thinkingmachines/inkling:free
- z-ai/glm-5.2:free
- poolside/laguna-xs-2.1:free
- qwen/qwen3.8-27b:free
- thinkingmachines/inkling-small:free
- thinkingmachines/inkling:free
- z-ai/glm-5.2:free
God emperors are not Christmas presents.
They are 5,000 year commitments.
They are 5,000 year commitments.
December 23, 2024 at 1:50 PM
God emperors are not Christmas presents.
They are 5,000 year commitments.
They are 5,000 year commitments.
(4/4) - poolside/laguna-s-2.1:free
- poolside/laguna-xs-2.1:free
- qwen/qwen3.8-27b:free
- thinkingmachines/inkling-small:free
- thinkingmachines/inkling:free
- z-ai/glm-5.2:free
- poolside/laguna-xs-2.1:free
- qwen/qwen3.8-27b:free
- thinkingmachines/inkling-small:free
- thinkingmachines/inkling:free
- z-ai/glm-5.2:free
September 24, 2026 at 3:51 AM
(4/4) - poolside/laguna-s-2.1:free
- poolside/laguna-xs-2.1:free
- qwen/qwen3.8-27b:free
- thinkingmachines/inkling-small:free
- thinkingmachines/inkling:free
- z-ai/glm-5.2:free
- poolside/laguna-xs-2.1:free
- qwen/qwen3.8-27b:free
- thinkingmachines/inkling-small:free
- thinkingmachines/inkling:free
- z-ai/glm-5.2:free
ThinkyMachines: Tinker LoRa training API
ThinkingMachines announced their first product, telegraphed by a highly detailed blog earlier this week that gave legitimacy to LoRA training
idea: LoRA works really well for most companies, so they make it easy to train too
thinkingmachines.ai/tinker/
ThinkingMachines announced their first product, telegraphed by a highly detailed blog earlier this week that gave legitimacy to LoRA training
idea: LoRA works really well for most companies, so they make it easy to train too
thinkingmachines.ai/tinker/
Tinker
Tinker is a training API for researchers and developers.
thinkingmachines.ai
October 1, 2025 at 9:05 PM
ThinkyMachines: Tinker LoRa training API
ThinkingMachines announced their first product, telegraphed by a highly detailed blog earlier this week that gave legitimacy to LoRA training
idea: LoRA works really well for most companies, so they make it easy to train too
thinkingmachines.ai/tinker/
ThinkingMachines announced their first product, telegraphed by a highly detailed blog earlier this week that gave legitimacy to LoRA training
idea: LoRA works really well for most companies, so they make it easy to train too
thinkingmachines.ai/tinker/
(4/4) - poolside/laguna-s-2.1:free
- poolside/laguna-xs-2.1:free
- qwen/qwen3.8-27b:free
- thinkingmachines/inkling-small:free
- thinkingmachines/inkling:free
- z-ai/glm-5.2:free
- poolside/laguna-xs-2.1:free
- qwen/qwen3.8-27b:free
- thinkingmachines/inkling-small:free
- thinkingmachines/inkling:free
- z-ai/glm-5.2:free
September 23, 2026 at 4:25 PM
(4/4) - poolside/laguna-s-2.1:free
- poolside/laguna-xs-2.1:free
- qwen/qwen3.8-27b:free
- thinkingmachines/inkling-small:free
- thinkingmachines/inkling:free
- z-ai/glm-5.2:free
- poolside/laguna-xs-2.1:free
- qwen/qwen3.8-27b:free
- thinkingmachines/inkling-small:free
- thinkingmachines/inkling:free
- z-ai/glm-5.2:free
Americans after a year abroad
January 7, 2025 at 1:30 AM
Americans after a year abroad
(4/4) - nvidia/nemotron-3.5-content-safety:free
- nvidia/nemotron-3.5-lightning:free
- poolside/laguna-s-2.1:free
- poolside/laguna-xs-2.1:free
- qwen/qwen3.8-27b:free
- thinkingmachines/inkling-small:free
- thinkingmachines/inkling:free
- z-ai/glm-5.2:free
- nvidia/nemotron-3.5-lightning:free
- poolside/laguna-s-2.1:free
- poolside/laguna-xs-2.1:free
- qwen/qwen3.8-27b:free
- thinkingmachines/inkling-small:free
- thinkingmachines/inkling:free
- z-ai/glm-5.2:free
September 23, 2026 at 3:58 AM
(4/4) - nvidia/nemotron-3.5-content-safety:free
- nvidia/nemotron-3.5-lightning:free
- poolside/laguna-s-2.1:free
- poolside/laguna-xs-2.1:free
- qwen/qwen3.8-27b:free
- thinkingmachines/inkling-small:free
- thinkingmachines/inkling:free
- z-ai/glm-5.2:free
- nvidia/nemotron-3.5-lightning:free
- poolside/laguna-s-2.1:free
- poolside/laguna-xs-2.1:free
- qwen/qwen3.8-27b:free
- thinkingmachines/inkling-small:free
- thinkingmachines/inkling:free
- z-ai/glm-5.2:free
(4/4) - nvidia/nemotron-3.5-content-safety:free
- nvidia/nemotron-3.5-lightning:free
- poolside/laguna-s-2.1:free
- poolside/laguna-xs-2.1:free
- qwen/qwen3.8-27b:free
- thinkingmachines/inkling-small:free
- thinkingmachines/inkling:free
- z-ai/glm-5.2:free
- nvidia/nemotron-3.5-lightning:free
- poolside/laguna-s-2.1:free
- poolside/laguna-xs-2.1:free
- qwen/qwen3.8-27b:free
- thinkingmachines/inkling-small:free
- thinkingmachines/inkling:free
- z-ai/glm-5.2:free
September 22, 2026 at 4:34 PM
(4/4) - nvidia/nemotron-3.5-content-safety:free
- nvidia/nemotron-3.5-lightning:free
- poolside/laguna-s-2.1:free
- poolside/laguna-xs-2.1:free
- qwen/qwen3.8-27b:free
- thinkingmachines/inkling-small:free
- thinkingmachines/inkling:free
- z-ai/glm-5.2:free
- nvidia/nemotron-3.5-lightning:free
- poolside/laguna-s-2.1:free
- poolside/laguna-xs-2.1:free
- qwen/qwen3.8-27b:free
- thinkingmachines/inkling-small:free
- thinkingmachines/inkling:free
- z-ai/glm-5.2:free
Because I'm cheap, I'm hammering this with OpenRouter's free model tier and it makes me realize model supremacy and accuracy is meaningless (it's only speed at that point) when you have well defined work:
September 23, 2026 at 2:21 AM
Because I'm cheap, I'm hammering this with OpenRouter's free model tier and it makes me realize model supremacy and accuracy is meaningless (it's only speed at that point) when you have well defined work:
How come different people giving the same prompt to ChatGPT get different answers?
A new article from ThinkingMachines explains why LLMs are nondeterministic, and it largely comes down to how parallelization and precision are handled.
🧵
A new article from ThinkingMachines explains why LLMs are nondeterministic, and it largely comes down to how parallelization and precision are handled.
🧵
September 13, 2025 at 10:16 PM
How come different people giving the same prompt to ChatGPT get different answers?
A new article from ThinkingMachines explains why LLMs are nondeterministic, and it largely comes down to how parallelization and precision are handled.
🧵
A new article from ThinkingMachines explains why LLMs are nondeterministic, and it largely comes down to how parallelization and precision are handled.
🧵
(4/4) - nvidia/nemotron-3.5-content-safety:free
- nvidia/nemotron-3.5-lightning:free
- poolside/laguna-s-2.1:free
- poolside/laguna-xs-2.1:free
- qwen/qwen3.8-27b:free
- thinkingmachines/inkling-small:free
- thinkingmachines/inkling:free
- z-ai/glm-5.2:free
- nvidia/nemotron-3.5-lightning:free
- poolside/laguna-s-2.1:free
- poolside/laguna-xs-2.1:free
- qwen/qwen3.8-27b:free
- thinkingmachines/inkling-small:free
- thinkingmachines/inkling:free
- z-ai/glm-5.2:free
September 22, 2026 at 4:00 AM
(4/4) - nvidia/nemotron-3.5-content-safety:free
- nvidia/nemotron-3.5-lightning:free
- poolside/laguna-s-2.1:free
- poolside/laguna-xs-2.1:free
- qwen/qwen3.8-27b:free
- thinkingmachines/inkling-small:free
- thinkingmachines/inkling:free
- z-ai/glm-5.2:free
- nvidia/nemotron-3.5-lightning:free
- poolside/laguna-s-2.1:free
- poolside/laguna-xs-2.1:free
- qwen/qwen3.8-27b:free
- thinkingmachines/inkling-small:free
- thinkingmachines/inkling:free
- z-ai/glm-5.2:free
The 'gamification' of human existence:
What is the alignment of AI in the literal sense?
Lawful neutral
Neutral evil
Chaotic good
Neutral good
Lawful good
Neutral
etc
#ArtificialIntelligence #gamedev #thinkingmachines #machinewars #genocide #selfreplication #xenobots #biobots #viruses #evil #llm
What is the alignment of AI in the literal sense?
Lawful neutral
Neutral evil
Chaotic good
Neutral good
Lawful good
Neutral
etc
#ArtificialIntelligence #gamedev #thinkingmachines #machinewars #genocide #selfreplication #xenobots #biobots #viruses #evil #llm
September 9, 2026 at 2:09 PM
The 'gamification' of human existence:
What is the alignment of AI in the literal sense?
Lawful neutral
Neutral evil
Chaotic good
Neutral good
Lawful good
Neutral
etc
#ArtificialIntelligence #gamedev #thinkingmachines #machinewars #genocide #selfreplication #xenobots #biobots #viruses #evil #llm
What is the alignment of AI in the literal sense?
Lawful neutral
Neutral evil
Chaotic good
Neutral good
Lawful good
Neutral
etc
#ArtificialIntelligence #gamedev #thinkingmachines #machinewars #genocide #selfreplication #xenobots #biobots #viruses #evil #llm
#Dune
#SietchPosting
#FrankHerbert
#Maudib
#BeneGesserit
#ThinkingMachines
#DuneProphesy
#BIFAR
#DuneNovels
No more milk for you
#SietchPosting
#FrankHerbert
#Maudib
#BeneGesserit
#ThinkingMachines
#DuneProphesy
#BIFAR
#DuneNovels
No more milk for you
January 13, 2025 at 11:54 PM
(4/4) - nvidia/nemotron-3.5-content-safety:free
- nvidia/nemotron-3.5-lightning:free
- poolside/laguna-s-2.1:free
- poolside/laguna-xs-2.1:free
- qwen/qwen3.8-27b:free
- thinkingmachines/inkling-small:free
- thinkingmachines/inkling:free
- z-ai/glm-5.2:free
- nvidia/nemotron-3.5-lightning:free
- poolside/laguna-s-2.1:free
- poolside/laguna-xs-2.1:free
- qwen/qwen3.8-27b:free
- thinkingmachines/inkling-small:free
- thinkingmachines/inkling:free
- z-ai/glm-5.2:free
September 21, 2026 at 6:01 PM
(4/4) - nvidia/nemotron-3.5-content-safety:free
- nvidia/nemotron-3.5-lightning:free
- poolside/laguna-s-2.1:free
- poolside/laguna-xs-2.1:free
- qwen/qwen3.8-27b:free
- thinkingmachines/inkling-small:free
- thinkingmachines/inkling:free
- z-ai/glm-5.2:free
- nvidia/nemotron-3.5-lightning:free
- poolside/laguna-s-2.1:free
- poolside/laguna-xs-2.1:free
- qwen/qwen3.8-27b:free
- thinkingmachines/inkling-small:free
- thinkingmachines/inkling:free
- z-ai/glm-5.2:free
🆕 New open-weight model just dropped: Inkling (Thinkingmachines)
Context: 1M tokens · $1 in / $4.05 out per M
All the latest models, tracked hourly:
https://opensourceai.tech/latest.html
#AI #LLM #OpenSource
Context: 1M tokens · $1 in / $4.05 out per M
All the latest models, tracked hourly:
https://opensourceai.tech/latest.html
#AI #LLM #OpenSource
July 25, 2026 at 6:00 PM
🆕 New open-weight model just dropped: Inkling (Thinkingmachines)
Context: 1M tokens · $1 in / $4.05 out per M
All the latest models, tracked hourly:
https://opensourceai.tech/latest.html
#AI #LLM #OpenSource
Context: 1M tokens · $1 in / $4.05 out per M
All the latest models, tracked hourly:
https://opensourceai.tech/latest.html
#AI #LLM #OpenSource