chat is this real??? 128K context, int4 quantisation, 1B params, distilled from Llama 4
OPEN SOURCE
-
Groq Slashes Prices for GPT-OSS Models with Prompt Caching
By
–
Devs: GPT-OSS, but make it faster and cheaper.
— Groq Inc (@GroqInc) 16 octobre 2025
Groq: 🤓
Major price drop just hit both GPT-OSS models, with prompt caching rolling out. pic.twitter.com/ekCRDCt8WbDevs: GPT-OSS, but make it faster and cheaper. Groq: Major price drop just hit both GPT-OSS models, with prompt caching rolling out.
-
PyTorch and MLX improvements key to AI community progress
By
–
I wish they would finally realize that Their one secret weapon is @awnihannun and MLX but if they could improve both PyTorch and MLX it’d create much progress for the community
-
HuggingFace Team Plan and Dataset Access for Impact
By
–
Hey! is getting a Team plan an option? Otherwise we can look into granting some for impactful work => datasets @ huggingface[.]co
-
Local LLMs Becoming Accessible: The Windows XP Era Arrives
By
–
> the Windows XP era of
> local LLMs is almost here > we’re about to make
> “local AI, no headaches”
> the new default > soon you’ll fire up AI at home
> and boom, “it just works” > get ready
> it’s going to be glorious -
Nanochat d32 training completes with strong metrics improvement
By
–
nanochat d32, i.e. the depth 32 version that I specced for $1000, up from $100 has finished training after ~33 hours, and looks good. All the metrics go up quite a bit across pretraining, SFT and RL. CORE score of 0.31 is now well above GPT-2 at ~0.26. GSM8K went ~8% -> ~20%,
-
Own Your LLMs: Buy GPU for Local AI Deployment
By
–
gentle reminder on this beautiful morning: Buy a GPU and own your LLMs not just use them; own them
-
8B MoE Model Support Coming to Ollama Next Release
By
–
This is not the same model. The 8B MoE is not currently supported in ollama, but it should be in the next release.
