GeForce RTX 5060 Ti 16 GB
16 GB GDDR7 · 448 GB/s · 180 W
RTX 5060 Ti 16 GB · 64 GB RAM → gpt-oss-20b
GPU · NVIDIA
RTX 5060 Ti 16 GB for local LLMs: which models run?
With 16 GB of VRAM and 448 GB/s of bandwidth, the RTX 5060 Ti 16 GB runs models up to about gpt-oss-20b entirely on the GPU.
- VRAM16 GB GDDR7
- Bandwidth448 GB/s
- Board power180 W
- ArchitectureBlackwell
Specifications
- VRAM
- 16 GB
- Memory type
- GDDR7
- Memory bus
- 128-bit
- Bandwidth
- 448 GB/s
- Board power
- 180 W
- Backends
- CUDA, Vulkan
- Interface
- PCIe 5.0 x8
- Released
- April 2025
- Segment
- Consumer
- FP16 compute
- Not available
Official specData updated 24 days agoSource: NVIDIA specifications
What the RTX 5060 Ti 16 GB runs
| gpt-oss-20bMXFP4 · 8K~13 GB · 96–117 tok/s measured | Excellent |
|---|---|
| Gemma 2 9B ITQ8_0 · 8K~12.7 GB · 29–39 tok/s estimate | Excellent |
| Qwen3 8BQ8_0 · 8K~10.5 GB · 34–46 tok/s estimate | Excellent |
| Llama 3.1 8B InstructQ8_0 · 8K~10.2 GB · 36–47 tok/s estimate | Excellent |
| DeepSeek R1 Distill Llama 8BQ8_0 · 8K~10.2 GB · 36–47 tok/s estimate | Excellent |
| Qwen2.5 7B InstructQ8_0 · 8K~9.2 GB · 39–52 tok/s estimate | Excellent |
| Mistral 7B Instruct v0.3Q8_0 · 8K~9.2 GB · 39–52 tok/s estimate | Excellent |
| Gemma 3 4B ITQ8_0 · 8K~5.4 GB · 69–96 tok/s estimate | Excellent |
| Qwen3 4BQ8_0 · 8K~6.2 GB · 61–85 tok/s estimate | Excellent |
| Phi-4 Mini Instruct 3.8BQ8_0 · 8K~6 GB · 66–90 tok/s estimate | Excellent |
| Llama 3.2 3B InstructQ8_0 · 8K~5.1 GB · 77–107 tok/s estimate | Excellent |
| Qwen3 1.7BQ8_0 · 8K~3.7 GB · 120–173 tok/s estimate | Excellent |
| Llama 3.2 1B InstructQ8_0 · 8K~2.5 GB · 194–277 tok/s estimate | Excellent |
| Qwen3 0.6BQ8_0 · 8K~2.5 GB · 205–326 tok/s estimate | Excellent |
| Mistral Small 3.2 24B InstructIQ4_XS · 8K~14.6 GB · 24–32 tok/s estimate | Compatible |
| Qwen3 14BQ6_K · 8K~14 GB · 25–34 tok/s estimate | Compatible |
| DeepSeek R1 Distill Qwen 14BQ6_K · 8K~14.3 GB · 25–33 tok/s estimate | Compatible |
| Qwen2.5 14B InstructQ6_K · 8K~14.3 GB · 25–33 tok/s estimate | Compatible |
| Phi-4 14BQ6_K · 8K~14.2 GB · 25–33 tok/s estimate | Compatible |
| Mistral Nemo 12B InstructQ8_0 · 8K~14.9 GB · 24–32 tok/s estimate | Compatible |
| Gemma 3 12B ITQ8_0 · 8K~14.1 GB · 25–33 tok/s estimate | Compatible |
| Qwen3 30B-A3BQ3_K_M · 8K~15.4 GB · 91–142 tok/s estimate | Compatible with limits |
| Gemma 3 27B ITQ3_K_M · 8K~15.3 GB · 23–30 tok/s estimate | Compatible with limits |
| Mixtral 8x7B InstructQ3_K_M · 8K~21.6 GB · 9–17 tok/s estimate | CPU/GPU offload |
| Qwen3 32BQ3_K_M · 8K~18.6 GB · 5–9.5 tok/s estimate | CPU/GPU offload |
| DeepSeek R1 Distill Qwen 32BQ3_K_M · 8K~18.5 GB · 5–9.5 tok/s estimate | CPU/GPU offload |
| Qwen2.5 32B InstructQ3_K_M · 8K~18.5 GB · 5–9.5 tok/s estimate | CPU/GPU offload |
| Qwen2.5 Coder 32B InstructQ3_K_M · 8K~18.5 GB · 5–9.5 tok/s estimate | CPU/GPU offload |
| QwQ 32BQ3_K_M · 8K~18.5 GB · 5–9.5 tok/s estimate | CPU/GPU offload |
| Qwen3 Coder 30B-A3B InstructQ3_K_M · 8K~16 GB · 60–116 tok/s estimate | CPU/GPU offload |
| Gemma 2 27B ITQ3_K_M · 8K~16.5 GB · 11–19 tok/s estimate | CPU/GPU offload |
| gpt-oss-120bMXFP4 · 8K~63.2 GB · 8.5–17 tok/s estimate | Possible but slow |
| Llama 4 Scout 17B-16E InstructQ3_K_M · 8K~55.7 GB · 3–5.5 tok/s estimate | Possible but slow |
| Qwen2.5 72B InstructQ3_K_M · 8K~38.2 GB · 0.9–1.7 tok/s estimate | Not recommended |
| Llama 3.3 70B InstructQ3_K_M · 8K~37 GB · 0.9–1.7 tok/s estimate | Not recommended |
| DeepSeek R1 Distill Llama 70BQ3_K_M · 8K~37 GB · 0.9–1.7 tok/s estimate | Not recommended |
| DeepSeek R1 (671B)Q8_0 · 8K~699 GB · No data | Incompatible |
| Qwen3 235B-A22BQ8_0 · 8K~247 GB · No data | Incompatible |
For each model, the highest-precision quantization that runs entirely in fast memory; otherwise the one with the best result. Speeds are ranges; "estimate" unless a benchmark exists for this exact hardware.
EstimateData updated 24 days agoSource: Run LLM Locally engine
Limits in plain words
16 GB of VRAM holds the weights and KV cache of models up to about gpt-oss-20b at Q4_K_M. Bigger models spill into system RAM and slow down sharply: generation speed is then limited by RAM bandwidth, not by the GPU.
Where to buy a RTX 5060 Ti 16 GB
Prices and links follow the market you choose.
No current offer imported for this market: the link opens a marketplace search.
Frequently asked questions
Which LLMs can the RTX 5060 Ti 16 GB run?
Entirely on the GPU: Qwen3 30B-A3B (Q3_K_M), Gemma 3 27B IT (Q3_K_M), Mistral Small 3.2 24B Instruct (IQ4_XS), gpt-oss-20b (MXFP4), Qwen3 14B (Q6_K), DeepSeek R1 Distill Qwen 14B (Q6_K), Qwen2.5 14B Instruct (Q6_K), Phi-4 14B (Q6_K). Larger models need CPU/GPU offload.
Can the RTX 5060 Ti 16 GB run a 70B model?
Not recommended: a 70B model at Q4_K_M needs about 45.1 GB; the RTX 5060 Ti 16 GB has 16 GB.
How is the speed estimated?
Token generation reads every active weight once per token, so it is limited by memory bandwidth (448 GB/s here). We apply an efficiency range per backend and label the result as an estimate until real benchmarks exist.