Granite 4.1: IBM's 8B Model Matching 32B MoE
1–10 of 223 posts
Re: Granite 4.1: IBM's 8B Model Matching 32B MoE
#2Wish they also released an embedding model, in the line of their previous: compact (while good)...
Re: Granite 4.1: IBM's 8B Model Matching 32B MoE
#3sounds 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.
Re: Granite 4.1: IBM's 8B Model Matching 32B MoE
#4I 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. Granite 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
Re: Granite 4.1: IBM's 8B Model Matching 32B MoE
#5Interesting 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...
Re: Granite 4.1: IBM's 8B Model Matching 32B MoE
#6I 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. Granite 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…
Yea, No doubt Qwen 3.6 open weights are far more strong
Re: Granite 4.1: IBM's 8B Model Matching 32B MoE
#7Wish they also released an embedding model, in the line of their previous: compact (while good)...
[dead]
Re: Granite 4.1: IBM's 8B Model Matching 32B MoE
#8I 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. Granite 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…
Yea, No doubt Qwen 3.6 open weights are far more strong
Why no doubt?
Re: Granite 4.1: IBM's 8B Model Matching 32B MoE
#9> Full stop.
Why people don't edit out obvious sloppification and expect to still have readers left
Re: Granite 4.1: IBM's 8B Model Matching 32B MoE
#10> Full stop. Why people don't edit out obvious sloppification and expect to still have readers left
So are we saying it's fine that the article is written by an LLM as long as it doesn't have the tell-tale signs of LLMs?