Granite 4.1: IBM's 8B Model Matching 32B MoE
- 2ndorderthought - 4195 sekunder sedanI test drove it yesterday. It's pretty impressive at 8b. Runs on commodity hardware quickly.
Qwen3.6 35b a3b is still my local champion but I may use this for auto complete and small tasks. It has recent training data which is nice. If the other small models got fine tuned on recent data I don't know if I would use this at all, but that alone makes it pretty decent.
The 4b they released was not good for my needs but could probably handle tool calls or something
- cbg0 - 2571 sekunder sedanThe real "sleeper" might be https://huggingface.co/ibm-granite/granite-vision-4.1-4b if the benchmarks hold up for such a small model against frontier models for table & semantic k:v extraction.
- Havoc - 4160 sekunder sedanInteresting to see a pivot away from MoE by both IBM and mistral while the larger classes of SOTA of models all seem to be sticking to it.
Quick vibe check of it- 8B @ Q6 - seems promising. Bit of a clinical tone, but can see that being useful for data processing and similar. You don't really want a LLM that spams you with emojis sometimes...
- tosh - 1797 sekunder sedanIBM announcement: https://research.ibm.com/blog/granite-4-1-ai-foundation-mode...
- agunapal - 1793 sekunder sedanIf you really think about why MoE came into existence, its to save significant cost during training, I don't think there was any concrete evidence of performance gains for comparable MoE vs dense models. Over the years, I believe all the new techniques being employed in post training have made the models better.
- 100ms - 3051 sekunder sedan> Full stop.
Why people don't edit out obvious sloppification and expect to still have readers left
- RugnirViking - 4372 sekunder sedansounds interesting. Here's hoping they release a 32B model, thats a pretty good sweet spot for feasibility of home setups.
edit: I just realised they do actually have a 30b release alongside this. Haven't tried it yet.
- mdp2021 - 4477 sekunder sedanWish they also released an embedding model, in the line of their previous: compact (while good)...
- whalesalad - 645 sekunder sedan[flagged]
Nördnytt! 🤓