12 GB VRAM (+1)
C
It fits through host-memory offload, and offload is the main reason performance drops.28.7 tok/s decode
~$329 MSRP
Can Gemma 2 9B run on GTX 1080 Ti 11GB?
BARELY — Tight on Memory
C55Usable
○Estimated from fit model
Gemma 2 9B needs ~12.9 GB VRAM. GTX 1080 Ti 11GB has 11.0 GB. With Q4_K_M quantization, expect ~28 tok/s.
Runtime: OllamaCapacity: OffloadBandwidth: MediumStack: BasicBottleneck: Host offload
Share:
Operating mode
Choose the run profile you care about
Interactive favors responsiveness, while light API and scale-out lean harder on serving readiness. The fit stays the same, but the recommendation lens changes.
Current mode
Balanced
Balanced for general local use. Keeps the ranking neutral across personal and serving workflows.
Select quantization to explore
Q4_K_M (Medium quality) — 12.9 GB, 28.0 tok/s, Very compromised (needs ~0.8 GB host RAM)
12.9 GB required11.0 GB available
117% VRAM needed
1.9 GB over capacity — needs offload or smaller quantization
Fit status
Very compromised (needs ~0.8 GB host RAM)
Decode
28.0 tok/s
TTFT
6916 ms
Safe context
8K
Memory
12.9 GB / 11.0 GB
Offload
10%
Memory breakdown
Weights5.5 GB
KV Cache5.1 GB
Runtime1.2 GB
Headroom1.1 GB
See how fast it feels
See how fast it feelsGemma 2 9B on GTX 1080 Ti 11GB
1st promptCold start — includes initialization
>What is local AI inference?
Local AI inference means running an AI language model directly on your own hardware — your laptop, desktop, or server — instead of sending requests to a remote cloud API.
When you run inference locally the model weights are loaded into your GPU or unified memory. Each token you generate requires reading those weights from memory, so memory bandwidth is the main bottleneck for decode speed.
Key benefits of running locally:
- Full privacy: your prompts never leave your machine
- No per-token cost or rate limits
- Works offline once the model is downloaded
- Latency depends only on your hardware
2nd promptWarm — model ready, no init overhead
>How much VRAM do I need?
It depends on the model size and quantization level. A rough rule of thumb:
Model size Q4 (4-bit) Q8 (8-bit) FP16
7B params ~4.3 GB ~7.5 GB ~14 GB
13B params ~7.9 GB ~13.9 GB ~26 GB
70B params ~42.7 GB ~74.9 GB ~140 GB
Most people use 4-bit quantization (Q4_K_M) which gives 90-95% of full quality at a fraction of the memory. A 24 GB GPU can comfortably run most 7B-13B models.
Estimated: 28.0 tok/s decode · 6.9s TTFT (warm) · 70 tok/s prefill
What limits this setup
It fits through host-memory offload, and offload is the main reason performance drops.
CPU or host-memory offload is active
About 10% of the working set spills out of accelerator memory, which usually hurts latency and sustained decode throughput.
Very little memory headroom
You can run the model, but there is not much room left for longer context, bigger batches, extra apps, or future model updates.
Older PCIe generation
PCIe 3.0 is workable, but it compounds the penalty when you offload heavily or try to scale across multiple cards.
Best improvement path
Remove offload with more accelerator memory
Prioritize a GPU or unified-memory tier that fits the whole model natively. Removing offload usually helps more than small compute gains.
Buy headroom, not only minimum fit
A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.
Increase host RAM if you keep offloading
This setup may need roughly 0.8 GB of extra host RAM just for the offloaded portion, before OS and other tools.
Performance by workload
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | B | Tight fit | 54.6 tok/s | 1934 ms | 8K |
| Coding | C | Very compromised (needs ~0.8 GB host RAM) | 28.0 tok/s | 6916 ms | 8K |
| Agentic Coding | F | Too heavy | 13.4 tok/s | 20958 ms | 8K |
| Reasoning | C | Very compromised (needs ~0.8 GB host RAM) | 28.0 tok/s | 8173 ms | 8K |
| RAG | F | Too heavy | 13.4 tok/s | 26197 ms | 8K |
Quantization options
How Gemma 2 9B (9B params) fits at each quantization level on GTX 1080 Ti 11GB (11.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 3.5 GB | Low | B65 |
Q3_K_S | 3 | 4.4 GB | Low | B67 |
NVFP4 | 4 | 5.0 GB | Medium | B67 |
Q4_K_M | 4 | 5.5 GB | Medium | B67 |
Q5_K_M | 5 | 6.5 GB | High | B67 |
Q6_KBest for your GPU | 6 | 7.4 GB | High | B66 |
Q8_0 | 8 | 9.6 GB | Very High | F0 |
F16 | 16 | 18.5 GB | Maximum | F0 |
Get started
Copy-paste commands to run Gemma 2 9B on your machine.
Run
ollama run gemma2Upgrade options
Hardware that runs Gemma 2 9B well
16 GB VRAM (+5)
B
Removes host-memory offload, which is usually the single biggest latency and throughput win.53.1 tok/s decode
Removes host-memory offload, which is usually the single biggest latency and throughput win.
Raises estimated decode speed by about 90%.
~$449 MSRP
16 GB VRAM (+5)
B
Removes host-memory offload, which is usually the single biggest latency and throughput win.40.2 tok/s decode
Removes host-memory offload, which is usually the single biggest latency and throughput win.
Raises estimated decode speed by about 44%.
~$499 MSRP