/lmg/ recommended models

The number of gigabytes in parentheses is the minimum amount of memory (VRAM + RAM) required to run the model at reasonable quant. For smaller models this is widely considered to be at least Q4_K_M. Large models can be quanted to 1 bit while remaining coherent but the exact impact on their performance, especially on long-context tasks, is still unexplored. With more memory you'll be able to fit more context. Using a smaller quant will make the model dumber.

Ideally the entire model fits in your VRAM. You can cope by loading parts of the model into RAM instead but it will be much slower.

MoE (mixture of experts) models don't use all of their parameters for each token so they are much faster than a dense model of the same size. Because of this loading a part of the model into RAM instead of VRAM is viable. All of the large models listed here are MoE. If you're using llama-server from llama.cpp it will automatically load the model in the most optimal way for your hardware. You should only set the preferred context size because otherwise it defaults to 4096 if you're short on VRAM.

ERP

• Newfags start here: Gemma 4 31B (24GB) / Gemma 4 12B (12GB) - Gold standard for VRAMlets right now. Supports vision so it can comment on your dick pics. Anons often say that for this use case it's as good as much larger models. You can also try the MoE and smaller versions listed below.
• GLM-4.5 Air (80GB) - Older model but there's not much else to fill this gap. Like Gemma its pretraining doesn't seem to have been filtered at all. MoE model.
• GLM-4.6 (200GB) / 4.7 - Same as the above but even more parameters and thus smarter. 4.7 has better benchmark scores but some Anons think that it's more safetyslopped.
• Kimi K3 / Kimi K2.7 (400GB) - If you're running this you're not reading this rentry.

Programming & General

Like most benchmarks, public programming benchmarks have found their way into the training dataset of most models. In my experience, if you work on anything other than webshit, bigger model = better despite the benchmark scores. Test them yourself on your own codebases.

For general assistant and "claw" type shit that searches the web and makes tool calls small models are good enough.

• Kimi K3 (1TB) - Fable at home. Supports vision.
• GLM 5.2 (300GB) - Opus at home but no vision.
• DeepSeek V4 Flash 0731 (200GB) - Sonnet at home but no vision.
• Qwen Series - Benchmaxxed models with an impressive lack of world knowledge compared to similarly sized models from other labs but they are often better at programming. Supports vision.
  • Qwen3.8 2.4T A95B (1TB)
  • Newfags start here: Qwen3.8 27B (24GB)
  • Qwen3.6 35B A3B (24GB) - Faster but dumber MoE version of the above.
  • Qwen3.5 9B (12GB) / Qwen3.5 4B (8GB) / Qwen3.5 2B (4GB) / Qwen3.5 0.8B (2GB) - Performance drops sharply here but they might be useful for very simple tasks. If you want to use them you should use bigger quants like Q8 for the smallest models.
• Gemma 4 Series - If you want to discuss obscure animu that Qwen doesn't know about Gemma probably has you covered. Supports vision.
  • Gemma 4 31B (24GB)
  • Gemma 4 26B A4B (24GB) - Faster but dumber MoE version of the above.
  • Gemma 4 12B (12GB) - Smaller dense version.
  • Gemma 4 E4B (12GB) / Gemma 4 E2B (8GB) - Similar to the Qwens above. I wouldn't use these unless you're desperate.