<8B multilingual models for language learning chatbots
I am currently looking for a model that can run on my phone, it could be <8b or even <4b. It should have a reduced positivity/yes-man bias. I am at a point in my language learning journey where it's more effective to learn a language through trying to actually construct a sentence (which is often through interaction) instead of just reading. Since there are times I am offline, a local LLM that is competent at multiple languages and decent at simulating characters texting would be a great help.
Gemma 4 e2b and e4b are designed to work on phones.
I actually (just last night) abliterated a Qwen3.5-2B for this sort of purpose (well, more specifically, to fit neatly into a socket for a project). It's fast and light, cooked for edge devices, and should have inherited all of base Qwen's tricks (~200 languages, vision etc) polaris-heretic-Q4_K_M-GGUF
Try it and see if it works? I inadvertently made it really fucking love dotpoints (GPT-OSS 20B disease) so am trying to unfuck it right now.
Else - I can recommend something like Granite-4H or the old Qwen3-4B 2507 instruct
granite-4.1-3b-heretic.i1-Q4_K_M
Qwen3-4B 2507 instruct
Thanks! I can't wait to try them. Though what differences do you find between Granite-4H and Qwen3-4B 2507?
Granite is much more straight laced. Qwen is more expressive. Honestly, it reminds me a lot of early days with GPT 4 class models (and the benchmarks show it about matches that, too).
ministral3-3b at crappy quants is better than internet search (faster). terrible for agentic stuff, but low thought tasks that you want to get though fast, this is perfect