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

Original article on IBM research

Hugging face weights: https://huggingface.co/collections/ibm-granite/granite-41-la...

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...

The article makes some good points about model design (how different size models within a family can get similar results, how to filter out hallucination, math result reinforcement), so that's worth understanding. It's analyzing a paper, which only discussed 3 sizes of the same model family. But what the article doesn't say is, compared to other model families, Granite 4.1 8B sucks. The only benchmark it does well at compared to other models is non-hallucination and instruction following. Qwen 3.5 4B (among other models) easily outclass it on every other metric.

This article teaches a valuable lesson about reading articles in general. You can take useful information away from them (yes, despite being written by LLM). But you should also use critical thinking skills and be proactive to see if the article missed anything you might find relevant.

Why people don't edit out obvious sloppification and expect to still have readers left

I ran it in LM Studio and got a pleasingly abstract pelican on a bicycle (genuinely not bad for a tiny 3B model - it can at least output valid SVG): https://gist.github.com/simonw/5f2df6093885a04c9573cf5756d34...

I have been using it with their Chunkless RAG concept and it is fitting very well! (for curious https://github.com/scub-france/Docling-Studio)

I convinced that SLM are a real parto of solution for true integrated AI in process...

> While reasoning models have grown in popularity in recent years, their abilities aren’t always the most efficient way to get a result. In enterprise settings, token costs and speed are often as important as performance. That is why turning to less expensive, non-reasoning models with similar benchmark performance for select tasks like instruction following and tool calling makes sense for enterprise users.

I guess they currently don't have the ability to do proper RLVR.

The gap that still matters most isn't intelligence — it's consistency on structured output. When you chain 5+ tool calls in sequence, even a small per-call reliability difference compounds fast. Would love to see Granite 4.1 benchmarked specifically on multi-step function calling rather than just general benchmarks.

Link to HF collection: https://huggingface.co/collections/ibm-granite/granite-41-la...

If techniques existed to shift from "guess the next highly probable" token to "guess the best next logical step", as some interpreted said research, should not that be the foremost objective?

edit: I just realised they do actually have a 30b release alongside this. Haven't tried it yet.

An interesting choice

Then something broke. The RLHF stage, while improving chat quality, caused math benchmark scores to drop. GSM8K and DeepMind-Math both regressed."

Observation: Math (which when fully decomposed, results in Logic) is at the core of how computers (traditional/older, non-LLM, programming languages work. If an LLM gets Math training wrong at any stage for any reason, then, in my opinion, that should be viewed as something that needs to be fixed at a lower level, not a higher one; not a later training level...

I think it would be interesting exercise to train an LLM that only deals in simple Math, simple English, and only the ability to compute simple equations (+,-,x,/)... like, what's the absolute minimum in terms of text and layers necessary to train a model like that?

I think some interesting understandings could be potentially be had by experimentation like that...

I myself would love a pure (simplest, smallest possible)

Text-to-Math only LLM (TTMLLM, TTMSLM?)

, along with all of the necessary corpuses (which would ideally be as small as possible) and instructions necessary to train such an LLM...

https://arxiv.org/pdf/2401.16818

With those results, I would've already done that in any models I got to train. There's also the principle that the LLM's are often better at what they saw last in their training set. That also justifies putting more logic, code, and math in at the end for an analytical or coding model. So, a few precedents for that technique already.

Granite 4.1 8B: "I apologize for the confusion earlier. Let's clarify the derivation of the VIDEO__MASK_00b based on the description "Bits 5-6 indicate the video mode" from the equipment_list section.

Given that bits 5 and 6 are used for video mode, we need to create a mask that isolates these two bits:

Bit 5 is the least significant bit of the group (2^5 = 32 decimal, 0b00100000 in 8-bit form). Bit 6 is the next bit up (2^6 = 64 decimal, 0b01000000 in 8-bit form). Combining these bits: ...

Therefore, the correct mask for VIDEO_MASK_00b should be 0x00C0"

Errors on top of errors when converting description into binary numbers. Its hopeless for basic task like parsing/generating headers :(

show me.