Best Local LLMs for the NVIDIA GeForce GTX 1080 Ti
Written by Jakub Rusinowski · Last updated October 7, 2026
Best all-round pick: Qwen 3 8B
The NVIDIA GeForce GTX 1080 Ti has 11 GB of VRAM, of which about 11 GB is available to a model. The largest model it can hold is Cosmos 3 Nano (16B, 10.5 GB at Q4_K_M).
Best models overall on the NVIDIA GeForce GTX 1080 Ti
| Model | Score | Memory at Q4_K_M | Context | Licence |
|---|---|---|---|---|
| Qwen 3 8B | 95.1 | 5.8 GB | 125K | Apache 2.0 |
| Qwen 3.5 14B | 94.4 | 9.3 GB | 125K | Apache 2.0 |
| Gemma 3 12B Instruct | 93.6 | 8 GB | 128K | Gemma |
| Qwen 3.5 14B | 93.5 | 9.3 GB | 125K | Apache 2.0 |
| Gemma 4 12B | 93.1 | 8 GB | 125K | Gemma License (commercial OK) |
| GLM-6 9B | 92.8 | 6.2 GB | 125K | MIT |
Best model by what you are doing
| Workload | Recommended on this GPU |
|---|---|
| Coding | Qwen 3 14B (95.9) Qwen3-Coder 8B (95.4) DeepSeek R1 Distill Qwen 14B (94.2) |
| General assistant | Qwen 3 8B (95.1) Qwen 3.5 14B (94.4) Gemma 3 12B Instruct (93.6) |
| Reasoning | Qwen 3 14B (96) DeepSeek R1 Distill Qwen 14B (94.4) Qwen 3.5 14B (94) |
| RAG | Qwen 3 14B (84.4) Qwen 3.5 14B (81.5) Gemma 4 12B (81.2) |
| Agents | GLM-6 9B (86.5) GLM-5 9B (85.1) Qwen 3.5 14B (84.6) |
| Vision | Qwen 3.5 14B (95.7) Gemma 4 12B (92.3) Gemma 4 12B (Unified) (92) |
What the NVIDIA GeForce GTX 1080 Ti cannot run
These models are strong picks generally but exceed the 11 GB this card makes available.
| Model | Needs at Q4_K_M | Short by |
|---|---|---|
| Gemma 4 27B ⭐ | 17.2 GB | ~6.2 GB |
| Mistral Small 3.1 24B | 15.1 GB | ~4.1 GB |
| Qwen3.8 27B | 17.6 GB | ~6.6 GB |
| Qwen 3.7 35B-A3B | 22 GB | ~11 GB |
How these numbers are calculated
- Usable memory is 11 GB of the card's 11 GB.
- Fit is measured at Q4_K_M — quantized weights plus KV cache plus 0.8 GB runtime overhead.
- Within this card's budget, models are ranked on how well they use the memory available, not on being small — so the recommendation scales with the hardware.
FAQ
What is the best LLM for the NVIDIA GeForce GTX 1080 Ti?
Qwen 3 8B is the strongest all-round pick that fits its 11 GB.
What is the largest model the NVIDIA GeForce GTX 1080 Ti can run?
Cosmos 3 Nano — 16B parameters, needing 10.5 GB at Q4_K_M.
How much of the NVIDIA GeForce GTX 1080 Ti's memory can a model actually use?
About 11 GB of its 11 GB, before the desktop and runtime overhead are accounted for.
Similar GPUs
- Best models for the NVIDIA GeForce RTX 2080 Ti
- Best models for the NVIDIA GeForce RTX 3080 Ti
- Best models for the NVIDIA GeForce RTX 3080 12GB
- Best models for the NVIDIA GeForce RTX 5070
By Workload
- Best local LLMs for coding
- Best local LLMs for general assistant
- Best local LLMs for reasoning
- Best local LLMs for rag