Hardware
GeForce RTX 2060 12GB
GeForce RTX 2060 12GB has 12 GB GDDR6 and 336 GB/s. See which open models fit, at which quant, and roughly how fast. Figures below use the default memory (12 GB), 32 GB system RAM, and DDR5-5600 for anything that spills. Updated 2026-10-17.
Memory12 GB GDDR6
Bandwidth336 GB/s
Kindgpu
Year2021
192-bit GDDR6 at 14 Gbps = 336 GB/s. Source.
RSS for new models on this device
Models that fit
| Model | Verdict | Quant | Context | tok/s |
|---|---|---|---|---|
| Qwen3 14B 14.8B | Tight fit | Q5_K_S | 4K | 17–23 |
| NousResearch Hermes 4 14B 14.8B | Tight fit | Q5_K_S | 4K | 17–23 |
| Ministral 3 14B Instruct 2512 13.5B | Tight fit | UD-Q5_K_XL | 8K | 17–23 |
| Ministral 3 14B Reasoning 2512 13.5B | Tight fit | UD-Q5_K_XL | 8K | 17–23 |
| Qwen2.5 14B Instruct 14.8B | Tight fit | Q4_K_M | 8K | 17–24 |
| DeepSeek R1 Distill Qwen 14B 14.8B | Tight fit | Q4_K_M | 8K | 17–24 |
| Qwen2.5 Coder 14B Instruct 128K 14.8B | Tight fit | Q4_K_M | 8K | 17–24 |
| phi 4 14.7B | Tight fit | Q4_K_M | 8K | 17–24 |
| gemma 4 12b it 11.9B | Tight fit | Q6_K | 8K | 14–19 |
| Devstral Small 2 24B Instruct 2512 23.6B | Tight fit | UD-IQ3_XXS | 8K | 17–23 |
| Mistral Small 3.2 24B Instruct 2506 23.6B | Tight fit | UD-IQ3_XXS | 8K | 17–23 |
| Magistral Small 2509 23.6B | Tight fit | UD-IQ3_XXS | 8K | 17–23 |
| Qwen3.8 27B 27.3B | Tight fit | UD-Q2_K_XL | 8K | 18–24 |
| Qwen2.5 32B Instruct 32.8B | Tight fit | IQ2_XXS | 4K | 18–25 |
| Qwen2.5 Coder 32B Instruct 32.8B | Tight fit | IQ2_XXS | 4K | 18–25 |
| Qwen3 32B 32.8B | Tight fit | UD-IQ2_XXS | 4K | 18–24 |
| Qwen3 VL 32B Instruct 32.8B | Tight fit | UD-IQ2_XXS | 4K | 18–24 |
| GLM 4 32B 0414 32.6B | Tight fit | UD-IQ2_XXS | 8K | 19–26 |
| GLM 4.6V Flash 9.4B | Tight fit | Q8_0 | 8K | 18–24 |
| GLM Z1 9B 0414 9.4B | Tight fit | Q8_0 | 8K | 18–24 |
| GLM 4 9B 0414 9.4B | Tight fit | Q8_0 | 8K | 18–24 |
| GLM 4.1V 9B Thinking 9.4B | Tight fit | Q8_0 | 8K | 18–24 |
| gemma 4 31B it 30.7B | Tight fit | UD-IQ2_XXS | 8K | 11–15 |
| Qwen3.5 9B 9.0B | Tight fit | Q8_0 | 8K | 19–26 |
| MiMo V2.6 Distill Qwen 9B 9.0B | Tight fit | Q8_0 | 8K | 19–26 |
| Ministral 3 8B Instruct 2512 8.5B | Tight fit | Q8_0 | 8K | 18–25 |
| Ministral 3 8B Reasoning 2512 8.5B | Tight fit | Q8_0 | 8K | 18–25 |
| Qwen3.5 27B 26.9B | Runs | UD-IQ2_XXS | 8K | 20–28 |
| Qwen3.6 27B 26.9B | Tight fit | UD-IQ2_XXS | 8K | 19–25 |
| Qwen3 VL 8B Instruct 8.2B | Tight fit | Q8_0 | 8K | 19–25 |
| DeepSeek R1 0528 Qwen3 8B 8.2B | Tight fit | Q8_0 | 8K | 19–25 |
| Qwen3 8B 8.2B | Tight fit | Q8_0 | 8K | 19–25 |
| Qwen3 VL 8B Thinking 8.2B | Tight fit | Q8_0 | 8K | 19–25 |
| gemma 3 27b it 27.0B | Runs | UD-IQ2_XXS | 8K | 15–21 |
| medgemma 27b text it 27.0B | Runs | UD-IQ2_XXS | 8K | 15–21 |
| Llama 3.1 8B Instruct 8.0B | Runs | UD-Q6_K_XL | 8K | 22–30 |
| DeepSeek R1 Distill Llama 8B 8.0B | Tight fit | Q8_0 | 8K | 19–26 |
| Apertus 8B Instruct 2509 8.1B | Tight fit | Q8_0 | 8K | 19–26 |
| GLM 4.7 Flash REAP 23B A3B 23.0B | Tight fit | Q3_K_S | 8K | 103–141 |
| Kwaipilot KAT Coder V2.5 Dev 34.7B | Tight fit | IQ2_XXS | 8K | 95–130 |
90 more models in the catalog do not fit this default profile, or ranked below the first 40 that do.
Example: Tight fit fully on your GeForce RTX 2060 12GB at Q5_K_S, 4K context, about 17–23 tok/s. Weights 9.56 GB plus 0.63 GB of KV cache — 10.6 GB of 10.9 GB usable. Weights shown in the verdict use GiB (the same 1024³ counting as GPU memory).