Home / AI GPUs / NVIDIA RTX 2060 12 GB

NVIDIA · GeForce

NVIDIA RTX 2060 12 GB

12 GB GDDR6 advertised VRAM. Usable memory for calculations is 90% of advertised capacity. This page is the chip + VRAM entity — not a single cooler SKU.

Models that fit (calculated)

ModelParamsQ4Q8FP16Max context in VRAM
Qwen2.5 0.5B Instruct494MFitsFitsFits32K
TinyLlama 1.1B Chat v1.01.1BFitsFitsFits2K
Llama 3.2 1B Instruct1.2BFitsFitsFits128K
Qwen2.5 1.5B Instruct1.5BFitsFitsFits32K
Qwen2.5-Coder 1.5B Instruct1.5BFitsFitsFits32K
SmolLM2 1.7B Instruct1.7BFitsFitsFits8K
Gemma 2 2B Instruct2.6BFitsFitsFits8K
Qwen2.5 3B Instruct3.1BFitsFitsFits32K
Llama 3.2 3B Instruct3.2BFitsFitsFits64K
Phi-3.5 Mini Instruct3.8BFitsFitsFits16K
Phi-3 Mini 128K Instruct3.8BFitsFitsFits16K
Phi-3 Mini 4K Instruct3.8BFitsFitsFits4K
Phi-4 Mini Instruct3.8BFitsFitsFits64K
Code Llama 7B Instruct6.7BFitsFitsOffload8K
Vicuna 7B v1.56.7BFitsFitsOffload4K
DeepSeek LLM 7B Chat6.9BFitsFitsOffload4K
StarCoder2 7B7.2BFitsFitsOffload16K
Falcon 7B Instruct7.2BFitsFitsOffload8K
OpenChat 3.5 7B7.2BFitsFitsOffload8K
Mistral 7B Instruct v0.37.3BFitsFitsOffload32K
OLMo 2 7B Instruct7.3BFitsFitsOffload4K
Falcon 3 7B Instruct7.5BFitsFitsOffload32K
DeepSeek R1 Distill Qwen 7B7.6BFitsFitsOffload64K
Qwen2.5 7B Instruct7.6BFitsFitsOffload32K
Qwen2.5-Coder 7B Instruct7.6BFitsFitsOffload32K
Qwen2.5-Math 7B Instruct7.6BFitsFitsOffload4K
Qwen2 7B Instruct7.6BFitsFitsOffload32K
DeepSeek R1 Distill Llama 8B8.0BFitsFitsOffload32K
Hermes 3 Llama 3.1 8B8.0BFitsFitsOffload32K
Llama 3.1 8B Instruct8.0BFitsFitsOffload32K
Llama 3 8B Instruct8.0BFitsFitsOffload8K
Qwen3 8B8.2BFitsFitsOffload40K
Yi 1.5 9B Chat8.8BFitsOffloadOffload4K
Gemma 2 9B Instruct9.2BFitsOffloadOffload8K
GLM-4-9B-04149.4BFitsOffloadOffload32K
GLM-4 9B Chat9.4BFitsOffloadOffload8K
Falcon 3 10B Instruct10BFitsOffloadOffload16K
SOLAR 10.7B Instruct11BFitsOffloadOffload4K
Mistral Nemo 12B Instruct12BFitsOffloadOffload16K
Code Llama 13B Instruct13BFitsOffloadOffload4K
Vicuna 13B v1.513BFitsOffloadOffload4K
OLMo 2 13B Instruct14BOffloadOffloadOffload2K
Phi-3 Medium 128K Instruct14BFitsOffloadOffload8K
Phi-3 Medium 4K Instruct14BFitsOffloadOffload4K
DeepSeek R1 Distill Qwen 14B15BFitsOffloadNo8K
Phi-415BFitsOffloadNo8K
Qwen2.5 14B Instruct15BFitsOffloadNo8K
Qwen3 14B15BFitsOffloadNo16K
StarCoder2 15B16BOffloadOffloadNo16K
GPT-OSS 20B22BOffloadOffloadNo
Mistral Small 24B Instruct24BOffloadOffloadNo
Gemma 2 27B Instruct27BOffloadNoNo
DeepSeek R1 Distill Qwen 32B33BOffloadNoNo
Qwen2.5 32B Instruct33BOffloadNoNo
Qwen2.5-Coder 32B Instruct33BOffloadNoNo
QwQ 32B33BOffloadNoNo
Qwen3 32B33BOffloadNoNo
Code Llama 34B Instruct34BOffloadNoNo
Yi 1.5 34B Chat34BOffloadNoNo
Mixtral 8x7B Instruct47BNoNoNo
DeepSeek R1 Distill Llama 70B71BNoNoNo
Hermes 3 Llama 3.1 70B71BNoNoNo
Llama 3.1 70B Instruct71BNoNoNo
Llama 3.3 70B Instruct71BNoNoNo
Qwen2.5 72B Instruct73BNoNoNo
GPT-OSS 120B117BNoNoNo
Mixtral 8x22B Instruct141BNoNoNo

Available graphics cards

These are Icecat product SKUs mapped to this chip. Different board-partner cards are not assumed to share a price. Amazon CTAs appear only for EXACT/HIGH matches that are not bundled accessories.

Find a GPU for a specific AI model

Sources

GPU identity and VRAM: Icecat structured specifications. Compatibility: RigForAI calculated estimate. Amazon: live affiliate match on individual SKUs, via /go/amazon/.