NVIDIA RTX 4060 Ti 16GB
The NVIDIA RTX 4060 Ti 16GB has 16 GB VRAM and 288 GB/s memory bandwidth. It can run 40 of our 70 tracked models natively in VRAM at 8k context.
With 16 GB GDDR6, the NVIDIA RTX 4060 Ti 16GB is a consumer-tier GPU that can run 40 models natively. It handles 30B-class models at Q4 quantization.
NVIDIA RTX 4060 Ti 16GB: 16GB GDDR6 at 288 GB/s — bandwidth is limited but capacity is king for LLM.
7B-14B at Q4 native. 27-32B at Q4 with CPU offload. ~8-12 t/s for 7B despite lower bandwidth.
Full CUDA support. Best budget 16GB option — bandwidth limits throughput but not model compatibility.
| Vendor | NVIDIA |
| Architecture | Ada Lovelace |
| VRAM | 16 GB |
| Memory type | GDDR6 |
| Memory bandwidth | 288 GB/s |
| Compute backend | CUDA |
| Tier | Consumer |
| Released | 2023 |
| Models (native) | 40 / 70 |
| Models (offload) | 9 / 70 |
Software: Full llama.cpp and Ollama support out of the box. CUDA 12.x recommended; driver ≥ 525 required.
Popular models for this GPU
Models this GPU runs natively in VRAM (40)
- Qwen 3.5 35B-A3B (MoE)35B · MMLU-Pro 84.2Q2_K · ~321 t/s
- Yi 1.5 34B Chat34.4B · MMLU-Pro 37.0Q2_K · ~25.4 t/s
- Qwen3 32B32.8B · MMLU-Pro 65.5Q2_K · ~26.7 t/s
- Qwen 2.5 32B Instruct32.5B · MMLU-Pro 69.0Q2_K · ~26.9 t/s
- Qwen 2.5 Coder 32B Instruct32.5B · MMLU-Pro 50.4Q2_K · ~26.9 t/s
- DeepSeek R1 Distill Qwen 32B32.5B · MMLU-Pro 65.0Q2_K · ~26.9 t/s
- Nemotron 3 Nano 30B32B · MMLU-Pro 78.3Q2_K · ~321 t/s
- Gemma 4 31B31B · MMLU-Pro 85.2Q2_K · ~28.2 t/s
- Qwen3 30B-A3B (MoE)30B · MMLU-Pro 61.5Q2_K · ~321 t/s
- Gemma 2 27B Instruct27.2B · MMLU-Pro 38.0Q2_K · ~32.2 t/s
- Gemma 3 27B Instruct27B · MMLU-Pro 67.5Q3_K_M · ~24.8 t/s
- Qwen 3.6 27B27B · MMLU-Pro 86.2Q3_K_M · ~24.8 t/s
- Gemma 4 26B (MoE)26B · MMLU-Pro 82.6Q3_K_M · ~193.9 t/s
- Mistral Small 3.1 24B Instruct24B · MMLU-Pro 66.8NVFP4 · ~24 t/s
- Mistral Small 22B22.2B · MMLU-Pro 49.2NVFP4 · ~25.9 t/s
- GPT-OSS 20B21B · MMLU-Pro 67.9NVFP4 · ~158.4 t/s
- Qwen3 14B14.8B · MMLU-Pro 61.0NVFP4 · ~38.9 t/s
- Qwen 2.5 14B Instruct14.7B · MMLU-Pro 63.7NVFP4 · ~39.2 t/s
- Phi-4 14B Instruct14B · MMLU-Pro 70.4NVFP4 · ~41.1 t/s
- Mistral Nemo 12B Instruct12.2B · MMLU-Pro 35.6NVFP4 · ~47.2 t/s
- Gemma 3 12B Instruct12.2B · MMLU-Pro 60.6NVFP4 · ~47.2 t/s
- Gemma 2 9B Instruct9.2B · MMLU-Pro 32.0NVFP4 · ~62.6 t/s
- Llama 3.1 8B Instruct8B · MMLU-Pro 48.3NVFP4 · ~72 t/s
- DeepSeek R1 Distill Llama 8B8B · MMLU-Pro 41.0NVFP4 · ~72 t/s
- Qwen3 8B8B · MMLU-Pro 56.7NVFP4 · ~72 t/s
- Qwen 2.5 7B Instruct7.6B · MMLU-Pro 56.3NVFP4 · ~75.8 t/s
- Mistral 7B Instruct v0.37.25B · MMLU-Pro 30.0NVFP4 · ~79.4 t/s
- Gemma 3 4B Instruct4B · MMLU-Pro 43.6BF16 · ~36 t/s
- Gemma 4 E4B4B · MMLU-Pro 69.4BF16 · ~36 t/s
- Phi-3.5 Mini Instruct3.8B · MMLU-Pro 47.4BF16 · ~37.9 t/s
- Llama 3.2 3B Instruct3.2B · MMLU-Pro 24.0BF16 · ~45 t/s
- Qwen 2.5 3B Instruct3.1B · MMLU-Pro 32.4FP32 · ~23.2 t/s
- Gemma 2 2B Instruct2.6B · MMLU-Pro 17.8FP32 · ~27.7 t/s
- Gemma 4 E2B2B · MMLU-Pro 60.0FP32 · ~36 t/s
- SmolLM2 1.7B Instruct1.7B · MMLU-Pro 19.0FP32 · ~42.4 t/s
- Qwen 2.5 1.5B Instruct1.5B · MMLU-Pro 16.8FP32 · ~48 t/s
- Llama 3.2 1B Instruct1.24B · MMLU-Pro 12.5FP32 · ~58.1 t/s
- Gemma 3 1B Instruct1B · MMLU-Pro 14.7FP32 · ~72 t/s
- Qwen 2.5 0.5B Instruct0.5B · MMLU-Pro 10.0FP32 · ~144 t/s
- SmolLM2 360M Instruct0.36B · MMLU-Pro 8.0FP32 · ~200 t/s
Models that fit with CPU offload (9)
These use system RAM for layers that don't fit in VRAM — expect much slower inference.
- GLM-4.5 Air 106B106B · MMLU-Pro 81.4Q2_K · ~18.2 t/s
- GLM-4.6V 106B106B · MMLU-Pro 79.9Q2_K · ~18.2 t/s
- Qwen 2.5 72B Instruct72B · MMLU-Pro 71.1Q3_K_M · ~2.3 t/s
- Llama 3.3 70B Instruct70B · MMLU-Pro 68.9Q3_K_M · ~2.4 t/s
- DeepSeek R1 Distill Llama 70B70B · MMLU-Pro 70.0Q3_K_M · ~2.4 t/s
- Llama 3.1 70B Instruct70B · MMLU-Pro 66.4Q3_K_M · ~2.4 t/s
- Mixtral 8x7B Instruct v0.146.7B · MMLU-Pro 29.7NVFP4 · ~11.2 t/s
- Command-R 35B35B · MMLU-Pro 33.0NVFP4 · ~4.1 t/s
- Qwen 3.6 35B35B · MMLU-Pro 85.2NVFP4 · ~4.1 t/s
Too large for this GPU (21)
- Mixtral 8x22B Instruct v0.1
- Llama 3.1 405B Instruct
- DeepSeek V3 671B
- DeepSeek R1 671B
- Llama 4 Scout 109B
- Llama 4 Maverick 400B
- Qwen3 235B-A22B (MoE)
- MiniMax M1 456B
- GPT-OSS 120B
- GLM-4.5 355B
- GLM-4.6 355B
- GLM-4.7 358B
- Qwen 3.5 122B-A10B (MoE)
- MiniMax M2.5 229B
- GLM-5 744B
- MiniMax M2.7 229B
- Nemotron 3 Super 120B
- Kimi K2.6
- GLM-5.1 754B
- DeepSeek V4 Pro 1.6T
- DeepSeek V4 Flash 284B
Compare NVIDIA RTX 4060 Ti 16GB with other GPUs
Frequently asked questions
- How much VRAM does the NVIDIA RTX 4060 Ti 16GB have?
- The NVIDIA RTX 4060 Ti 16GB has 16 GB of GDDR6 with 288 GB/s memory bandwidth.
- What is the NVIDIA RTX 4060 Ti 16GB best for?
- With 16 GB of VRAM, the NVIDIA RTX 4060 Ti 16GB handles smaller models (7B–14B) at Q4–Q5 quantization — ideal for entry-level local LLM experimentation and lightweight inference.
- What LLMs can the NVIDIA RTX 4060 Ti 16GB run locally?
- The NVIDIA RTX 4060 Ti 16GB can run 40 of the 70 open-weight models tracked by CanItRun natively in VRAM at 8k context. Top options include: Llama 3.1 8B Instruct at NVFP4, Llama 3.2 3B Instruct at BF16, Llama 3.2 1B Instruct at FP32.
- Can the NVIDIA RTX 4060 Ti 16GB run Llama 3.3 70B Instruct?
- The NVIDIA RTX 4060 Ti 16GB can run Llama 3.3 70B Instruct with CPU offload at Q3_K_M quantization, but inference will be slower than native VRAM execution.
- Can the NVIDIA RTX 4060 Ti 16GB run Qwen 3.6 27B?
- Yes. The NVIDIA RTX 4060 Ti 16GB runs Qwen 3.6 27B natively in VRAM at Q3_K_M quantization, achieving approximately 24.8 tokens per second.
- Can the NVIDIA RTX 4060 Ti 16GB run Llama 3.1 8B Instruct?
- Yes. The NVIDIA RTX 4060 Ti 16GB runs Llama 3.1 8B Instruct natively in VRAM at NVFP4 quantization, achieving approximately 72 tokens per second.