NVIDIATuring

Best AI Models for NVIDIA GeForce RTX 2080 Ti (11.0GB)

VRAM:11.0 GB GDDR6·Bandwidth:616.0 GB/s·CUDA Cores:4,352·TDP:250W·MSRP:$999

Turing 11 GB: has Tensor Cores and flash-attention (cc 7.5) — the cheapest used card that still runs modern FP16 kernels well.

11 GB is an entry-level tier for local AI. You can run small 7B models at lower quantization levels, which is great for experimenting but comes with quality and speed trade-offs.

With 11 GB, you're limited to smaller models and lower quantization levels, but it's still enough for a meaningful local AI experience. Phi 3 Mini (3.8B) and similar compact models run well at Q4_K_M. For 7B models like Mistral 7B and Llama 3 8B, you'll need Q2_K or Q3_K_M quantization, which reduces output quality. Think of this tier as ideal for learning and experimentation rather than production workloads.

Runs Well

  • 3B–4B models at Q4–Q5 quality
  • 7B models at Q2–Q3 (usable but reduced quality)
  • Quick experiments and learning

Challenging

  • 7B models at Q4+ (VRAM too tight)
  • Any model above 7B parameters
  • Long context windows even with small models

What LLMs Can NVIDIA GeForce RTX 2080 Ti Run?

79 models · 9 excellent · 11 good

Showing compatibility for NVIDIA GeForce RTX 2080 Ti

LLM models compatible with NVIDIA GeForce RTX 2080 Ti — ranked by performance
ModelVRAMGrade
Q4_K_M·79.4 t/s tok/s·262K ctx·FAIR FIT
5.0 GBB61
Phi 4 Reasoning14.7B
Q4_K_M·42.1 t/s tok/s·33K ctx·FAIR FIT
9.5 GBB63
Q4_K_M·80.2 t/s tok/s·4K ctx·FAIR FIT
5.0 GBB60
Q4_K_M·101.1 t/s tok/s·33K ctx·FAIR FIT
4.0 GBB51
CodeQwen1.5 7B7.3B
Q4_K_M·83.8 t/s tok/s·66K ctx·FAIR FIT
4.8 GBB58
Q4_K_M·86.7 t/s tok/s·4K ctx·FAIR FIT
4.6 GBB57
Q4_K_M·116.7 t/s tok/s·131K ctx·FAIR FIT
3.4 GBB46
Yi 6B Chat6.1B
Q4_K_M·98.4 t/s tok/s·4K ctx·FAIR FIT
4.1 GBB52
Gemma 3n E2B IT5.4B
Q4_K_M·111.5 t/s tok/s·FAIR FIT
3.6 GBB48
Q4_K_M·86.7 t/s tok/s·8K ctx·FAIR FIT
4.6 GBB57
Phi 3 Mini 4k Instruct3.8B
Q4_K_M·117.8 t/s tok/s·4K ctx·FAIR FIT
3.4 GBB46
Qwen3 4B4.0B
Q4_K_M·138.1 t/s tok/s·41K ctx·EASY RUN
2.9 GBC41
Yi 6B6.1B
Q4_K_M·98.4 t/s tok/s·4K ctx·FAIR FIT
4.1 GBB52
Q4_K_M·138.1 t/s tok/s·262K ctx·EASY RUN
2.9 GBC41
QwQ 32B32.8B
IQ2_XXS·40.6 t/s tok/s·41K ctx·FAIR FIT
9.8 GBB52
Gemma 3 4B IT4.3B
Q4_K_M·141.0 t/s tok/s·EASY RUN
2.8 GBC41

NVIDIA GeForce RTX 2080 Ti Specifications

Brand
NVIDIA
Architecture
Turing
Compute Capability
7.5 (CUDA SM version)
VRAM
11.0 GB GDDR6
Memory Bandwidth
616.0 GB/s
CUDA Cores
4,352
Tensor Cores
544
FP16 Performance
26.90 TFLOPS
TDP
250W
Release Date
2018-09-27
MSRP
$999

Get Started

Ollama (Recommended)

$curl -fsSL https://ollama.com/install.sh | sh
$ollama run llama3:8b

LM Studio

LM Studio

Download LM Studio, search for a model, and run it with one click.

GPUs to Consider Over NVIDIA GeForce RTX 2080 Ti

Similar GPUs and upgrades with more VRAM or higher bandwidth for AI

Frequently Asked Questions

Can NVIDIA GeForce RTX 2080 Ti run Gemma 3 12B IT?

Yes, the NVIDIA GeForce RTX 2080 Ti with 11 GB can run Gemma 3 12B IT, Gemma 4 12B IT, Mistral Nemo Instruct 2407, and 1045 other models. 74 models run at excellent quality, and 160 at good quality. Check the compatibility table above for the full list with VRAM usage and estimated speed.

Is NVIDIA GeForce RTX 2080 Ti good for AI?

The NVIDIA GeForce RTX 2080 Ti has 11 GB of GDDR6, making it usable for running local AI models. It supports 234 models at good quality or better. With 616.0 GB/s memory bandwidth, it delivers solid token generation speeds. You can run smaller models and experiment with quantized 7B models.

How many parameters can NVIDIA GeForce RTX 2080 Ti handle?

With 11 GB, the NVIDIA GeForce RTX 2080 Ti supports models from 1B to 7B parameters depending on quantization level. At Q4_K_M (the recommended sweet spot), you can fit roughly 18B parameters. Smaller 3B–7B models fit at Q3–Q4 quantization.

What quantization should I use on NVIDIA GeForce RTX 2080 Ti?

For the best balance of quality and speed on the NVIDIA GeForce RTX 2080 Ti, start with Q4_K_M — it preserves ~85% of the original model quality while keeping VRAM usage reasonable. If a model barely fits, drop to Q3_K_M — quality loss is noticeable but still useful for chat. Avoid Q2_K unless you just want to test whether a model works at all.

How fast is NVIDIA GeForce RTX 2080 Ti for AI inference?

With 616.0 GB/s memory bandwidth, the NVIDIA GeForce RTX 2080 Ti achieves approximately 89 tokens/sec on a 7B model at Q4_K_M — that's very fast, well above conversational speed. Token generation speed scales inversely with model size — smaller models are significantly faster.

tok/s = (616 GB/s ÷ model GB) × efficiency

Smaller models = faster inference. Memory bandwidth is the main bottleneck for token generation speed.

Estimated speed on NVIDIA GeForce RTX 2080 Ti

Real-world results typically within ±20%. Speed depends on quantization kernel, batch size, and software stack.

Learn more about tok/s estimation →

What's the best model for NVIDIA GeForce RTX 2080 Ti?

The top-rated models for the NVIDIA GeForce RTX 2080 Ti are Gemma 3 12B IT, Gemma 4 12B IT, Mistral Nemo Instruct 2407. The best choice depends on your use case: coding assistants benefit from code-tuned models, while general chat works well with instruction-tuned models like Llama or Qwen.

What power supply and cooling does NVIDIA GeForce RTX 2080 Ti need?

The NVIDIA GeForce RTX 2080 Ti has a TDP of 250 W. A good rule of thumb is to provide at least double the GPU's TDP to cover the rest of the system — that means a 550 W PSU or larger. A mid-tower case with one intake and one rear exhaust is usually sufficient. Keep dust filters clean, as sustained inference generates continuous heat rather than the brief spikes typical of gaming.

Anything to watch out for with NVIDIA GeForce RTX 2080 Ti?

Turing 11 GB: has Tensor Cores and flash-attention (cc 7.5) — the cheapest used card that still runs modern FP16 kernels well.