Advisor / Models
Local LLM models
Memory requirements, context limits and the hardware that runs each model.
13 models
| Model | Params | Smallest quant | Max context | Fits fully on |
|---|---|---|---|---|
| Gemma 4 26B-A4B | 25.81B MoE | 16.95 GB | 256k | 18 configs |
| Gemma 4 31B | 31.27B | 18.32 GB | 256k | 18 configs |
| Gemma 4 12B | 11.96B | 7.12 GB | 256k | 25 configs |
| Qwen3.6 27B | 27.78B | 16.82 GB | 1.01M | 18 configs |
| Qwen3.6 35B-A3B | 35.95B MoE | 22.13 GB | 1.01M | 16 configs |
| Qwen3.5 9B | 9.65B | 5.68 GB | 1.01M | 26 configs |
| Qwen3.5 4B | 4.66B | 2.74 GB | 1.01M | 26 configs |
| gpt-oss 20B | 20.91B MoE | 11.62 GB | 128k | 21 configs |
| gpt-oss 120B | 116.83B MoE | 62.77 GB | 128k | 9 configs |
| Qwen3-Coder 30B-A3B | 30.53B MoE | 18.56 GB | 1M | 18 configs |
| Mistral Small 3.2 24B | 24.01B | 14.33 GB | 128k | 18 configs |
| Qwen3-VL 8B | 8.77B | 5.03 GB | 1M | 25 configs |
| GLM-4.5-Air | 110.47B MoE | 72.98 GB | 128k | 8 configs |
By memory: 8 GB · 12 GB · 16 GB · 24 GB · 32 GB · 48 GB · 64 GB · 96 GB · 128 GB · 192 GB · 256 GB · 512 GB