GeForce GTX 1080 Ti
Local inference speed
llama.cpp decode speed (tok/s) - estimated
| Workload | tok/s |
|---|---|
| LLaMA 3 8B Q4 | 56.7 |
Estimated - Estimated from memory bandwidth (llama.cpp decode) · updated 2026-11-22
Stacks for the GeForce GTX 1080 Ti
Complete local setups that run on 11 GB
AI pair programming in your terminal with local models, fully private
A private AI assistant on Windows with document RAG - no CLI, no Docker, all desktop GUI
A private AI coding assistant in your editor
Prototype and deploy multi-agent RAG applications visually with local models
Unify multiple local and cloud models behind a single OpenAI-compatible API
GeForce GTX 1080 TiLink to this section
The GeForce GTX 1080 Ti is an NVIDIA GPU built on the Pascal architecture, released 2017-03-10. For running AI locally, the numbers that matter are its 11 GB of GDDR5X and 484.4 GB/s of memory bandwidth. VRAM decides which models fit at all; bandwidth sets how fast they generate text.
What you can run on 11 GBLink to this section
At Q4_K_M quantization (the usual local default), 11 GB holds models up to roughly 17B parameters, leaving headroom for context. On this card you can run, among others:
- DeepSeek-Coder-V2-Lite-Instruct - 15.7B parameters
- Apriel-v1.6-15B-Thinker - 15B parameters
- JiRackUltra_14b - 14.8B parameters
- Qwen2.5-14B-Instruct - 14.8B parameters
- Qwen2.5-Coder-14B-Instruct - 14.8B parameters
Larger models need a higher-VRAM card, a second GPU, or CPU offload (which is much slower). Check any specific model with the VRAM calculator, or see the full picture on what can I run.
Local LLM speed (LLaMA 3, llama.cpp)Link to this section
Single-stream token-generation throughput - estimated from memory bandwidth:
| Model (quant) | Speed on GeForce GTX 1080 Ti |
|---|---|
| Llama 3 8B (Q4_K_M) | 56.7 tok/s |
| Llama 3 8B (F16) | ✗ won't fit |
| Llama 3 70B (Q4_K_M) | ✗ won't fit |
Because decode is memory-bandwidth bound, the 484.4 GB/s figure is the best single predictor of chat speed on this card. Estimates are calibrated against measured RTX-40-series cards and are typically within ~15%.
Memory and powerLink to this section
- VRAM: 11 GB GDDR5X (352-bit bus)
- Bandwidth: 484.4 GB/s
- TDP: 250 W - a 600 W+ power supply is recommended
- Process: 16 nm
- Interface: PCIe 3.0 x16
Quantization and contextLink to this section
Quantization trades a little quality for a lot of VRAM. On 11 GB you can fit roughly a 17B model at Q4_K_M, about a 9B model at the higher-quality Q8, or a smaller model at full FP16. Longer context windows also consume VRAM (the KV cache grows with context length), so leave a few GB of headroom if you plan to use large prompts or many concurrent requests. For most chat and coding use, Q4_K_M on this card is the sweet spot between speed, quality, and the 11 GB budget.
How it comparesLink to this section
Similar cards for local AI, by VRAM and 8B-Q4 speed:
| GPU | VRAM | Bandwidth | Llama 3 8B Q4 |
|---|---|---|---|
| GeForce GTX 1080 Ti | 11 GB | 484.4 GB/s | 56.7 tok/s |
| NVIDIA RTX 2080 Ti | 11 GB | 616 GB/s | 72.1 tok/s |
| AMD Radeon RX 7700 XT | 12 GB | 432 GB/s | 50.6 tok/s |
| Arc A730M | 12 GB | 336 GB/s | 39.3 tok/s |
Bottom lineLink to this section
The GeForce GTX 1080 Ti is best for entry-level, budget-llm. With under 12 GB, stick to small quantized models (up to ~7B). If you need more, compare with NVIDIA RTX 2080 Ti and AMD Radeon RX 7700 XT.
SourcesLink to this section
- Specifications: RightNow GPU Database (TechPowerUp data)
- Benchmarks: GPU-Benchmarks-on-LLM-Inference (basis for the bandwidth estimate)
Specs and benchmarks last checked 2026-11-22. Verify current pricing before buying.
Frequently asked
Quick answers to common questions
How much VRAM does the GeForce GTX 1080 Ti have?
The GeForce GTX 1080 Ti has 11 GB of VRAM with 484.4 GB/s memory bandwidth.
What local AI models can run on the GeForce GTX 1080 Ti?
The GeForce GTX 1080 Ti with 11 GB VRAM can run many models depending on quantization. Models up to ~16B params may fit at Q4_K_M. Use our VRAM calculator to check specific models.
Is the GeForce GTX 1080 Ti good for local AI inference?
GeForce GTX 1080 Ti is best for entry-level, budget-llm. Check our hardware directory for alternatives with more VRAM.
Where can I buy the GeForce GTX 1080 Ti?
Check our buy links above for the best current prices on Amazon, Newegg, and B&H. Prices vary by retailer and availability.
How does the GeForce GTX 1080 Ti compare to other GPUs?
GeForce GTX 1080 Ti has 11 GB VRAM and 484.4 GB/s bandwidth. It works best with smaller quantized models. Browse our hardware directory for side-by-side comparisons.
What power supply do I need for the GeForce GTX 1080 Ti?
The GeForce GTX 1080 Ti has a TDP of 250W. A standard quality PSU of 650W+ should suffice. Always check the manufacturer's recommendations for your specific build.
Nearby options
Similar hardware and models that fit