Tested how OpenCode Works with SelfHosted LLMS: Qwen 3.5, 3.6, Gemma 4, Nemotron 3, GLM-4.7 Flash - v2

I have run two tests on each LLM with OpenCode to check their basic readiness and convenience: \- Create IndexNow CLI in Golang (Easy Task) and \- Create Migration Map for a website following SiteStructure Strategy. (Complex Task) Tested Qwen 3.5, & 3.6, Gemma 4, Nemotron 3, GLM-4.7 Flash and several other LLMs. Context size used: 25k-50k - varies between tasks and models. The result is in the table below, the most of exact quant names are in the speed test table. Hope you find it useful. \--- Here in v2 I added tests of \- Qwen 3.6 35b q3 and q4 => the result is worse then expected \- Qwen 3 Coder Next => very good result \- and Qwen 3.5 27b q3 Bartowsky => disappointed https://preview.redd.it/akly3cx1sowg1.png?width=687&format=png&auto=webp&s=5eb5f4868d87b5c78924916e9078b6f63e1d6d82 The speed of most of these selfhosted LLMs - on RTX 4080 (16GB VRAM) is below (to give you an idea how fast/slow each model is). Used llama.cpp with recommended temp, top-p and other params, and default memory and layers params. Finetuning these might help you to improve speed a bit. Or maybe a bit more than a bit :) https://preview.redd.it/uf1gszu8qowg1.png?width=661&format=png&auto=webp&s=7a0c9b6167ba582ad885640819754e46da28f735 My Takeaway from this test iteration: \- Qwen 3.5 27b is a very decent LLM (Unthloth's quants) that suit my hardware well. \- Qwen3 Coder Next is better then Qwen 3.5 and 3.6 35b. \- Qwen 3.5 and 3.6 35b are good, but not good enough for my tasks. \- Both Gemma 4 26b and 31b showed very good results too, though for self-hosing on 16GB VRAM the 31b variant is too big. \--- The details of each LLM behaviour in each test are here: [https://www.glukhov.org/ai-devtools/opencode/llms-comparison/](https://www.glukhov.org/ai-devtools/opencode/llms-comparison/)