What LLMs Can the RTX 2080 Ti 11GB Run?
The RTX 2080 Ti 11GB has 11 GB of VRAM and 616 GB/s of bandwidth. It runs 25 of 58 models fully at Q4_K_M with 8K context, up to Qwen 3 14B, and generates about 72 tokens/s on an 8B model.
25 of 58 models fit
RTX 2080 Ti 11GB (11.0 GB) at Q4_K_M with 8K context. Largest that fits fully: Qwen 3 14B.
| Model | Needs | Status | Speed | Best quant that fits |
|---|---|---|---|---|
| Ministral 3 14B | 9.7 GB | Fits | ~44 tok/s | Q4_K_M |
| Mistral Nemo 12B | 9.0 GB | Fits | ~49 tok/s | Q5_K_M |
| Gemma 3 12B | 8.8 GB | Fits | ~49 tok/s | Q5_K_M |
| Ministral 3 8B | 6.7 GB | Fits | ~68 tok/s | Q8_0 |
| Qwen 3 8B | 6.6 GB | Fits | ~70 tok/s | Q8_0 |
| Qwen 3.5 9B | 6.4 GB | Fits | ~70 tok/s | Q8_0 |
| Llama 3.1 8B | 6.3 GB | Fits | ~72 tok/s | Q8_0 |
| DeepSeek R1 Distill Llama 8B | 6.3 GB | Fits | ~72 tok/s | Q8_0 |
| Mistral 7B v0.3 | 5.7 GB | Fits | ~79 tok/s | Q8_0 |
| Gemma 4 E4B | 5.7 GB | Fits | ~78 tok/s | Q8_0 |
| Qwen 2.5 7B | 5.6 GB | Fits | ~81 tok/s | Q8_0 |
| DeepSeek R1 Distill Qwen 7B | 5.6 GB | Fits | ~81 tok/s | Q8_0 |
| Qwen 3 4B | 4.2 GB | Fits | ~126 tok/s | FP16 / BF16 |
| Phi-4 Mini | 4.1 GB | Fits | ~134 tok/s | FP16 / BF16 |
| Gemma 4 E2B | 4.0 GB | Fits | ~123 tok/s | Q8_0 |
| Gemma 3 4B | 3.7 GB | Fits | ~136 tok/s | FP16 / BF16 |
| Qwen 3.5 4B | 3.7 GB | Fits | ~140 tok/s | FP16 / BF16 |
| Ministral 3 3B | 3.5 GB | Fits | ~153 tok/s | FP16 / BF16 |
| Llama 3.2 3B | 3.5 GB | Fits | ~158 tok/s | FP16 / BF16 |
| Llama 3.2 1B | 1.7 GB | Fits | ~421 tok/s | FP16 / BF16 |
| Gemma 3 1B | 1.6 GB | Fits | ~542 tok/s | FP16 / BF16 |
| Qwen 2.5 14B | 10.7 GB | Tight fit | ~40 tok/s | IQ4_XS |
| DeepSeek R1 Distill Qwen 14B | 10.7 GB | Tight fit | ~40 tok/s | IQ4_XS |
| Phi-4 14B | 10.6 GB | Tight fit | ~40 tok/s | IQ4_XS |
| Qwen 3 14B | 10.5 GB | Tight fit | ~41 tok/s | IQ4_XS |
| Mixtral 8x7B | 28.0 GB | 37% on GPU | ~7.3 tok/s | – |
| Qwen 2.5 32B | 21.4 GB | 48% on GPU | ~3.5 tok/s | – |
| Qwen 2.5 Coder 32B | 21.4 GB | 48% on GPU | ~3.5 tok/s | – |
| DeepSeek R1 Distill Qwen 32B | 21.4 GB | 48% on GPU | ~3.5 tok/s | – |
| Qwen 3 32B | 21.4 GB | 48% on GPU | ~3.5 tok/s | – |
| Qwen 3.5 35B-A3B | 21.0 GB | 49% on GPU | ~33 tok/s | – |
| Qwen 3.6 35B-A3B | 21.0 GB | 49% on GPU | ~33 tok/s | – |
| Gemma 4 31B | 19.8 GB | 52% on GPU | ~4.0 tok/s | – |
| Qwen 3 30B-A3B | 18.8 GB | 55% on GPU | ~30 tok/s | – |
| Qwen3-Coder 30B-A3B | 18.8 GB | 55% on GPU | ~30 tok/s | – |
| Gemma 3 27B | 17.6 GB | 59% on GPU | ~5.1 tok/s | – |
| Qwen 3.5 27B | 16.9 GB | 61% on GPU | ~5.5 tok/s | – |
| Qwen 3.6 27B | 16.9 GB | 61% on GPU | ~5.5 tok/s | – |
| Qwen 3.8 27B | 16.9 GB | 61% on GPU | ~5.5 tok/s | – |
| Mistral Small 3.1 24B | 15.6 GB | 66% on GPU | ~6.7 tok/s | – |
| Gemma 4 26B-A4B | 15.6 GB | 66% on GPU | ~35 tok/s | Q2_K |
| gpt-oss-20b | 12.9 GB | 80% on GPU | ~56 tok/s | Q2_K |
| Kimi K2.6 | 566 GB | Too small | – | – |
| DeepSeek R1 671B | 380 GB | Too small | – | – |
| Llama 3.1 405B | 234 GB | Too small | – | – |
| Qwen 3.5 397B-A17B | 226 GB | Too small | – | – |
| DeepSeek V4 Flash | 161 GB | Too small | – | – |
| Qwen 3 235B-A22B | 135 GB | Too small | – | – |
| MiniMax-M2 | 133 GB | Too small | – | – |
| Qwen 3.5 122B-A10B | 70.2 GB | Too small | – | – |
| Mistral Small 4 119B | 68.2 GB | Too small | – | – |
| gpt-oss-120b | 67.2 GB | Too small | – | – |
| Llama 4 Scout | 64.0 GB | Too small | – | – |
| GLM-4.5-Air | 62.1 GB | Too small | – | – |
| Qwen3-Next 80B-A3B | 46.3 GB | Too small | – | – |
| Qwen 2.5 72B | 44.5 GB | Too small | – | – |
| Llama 3.3 70B | 43.2 GB | Too small | – | – |
| DeepSeek R1 Distill Llama 70B | 43.2 GB | Too small | – | – |
RTX 2080 Ti 11GB for local AI
Still fast for its age thanks to 616 GB/s of bandwidth, but 11 GB is an awkward size: it runs 8B models quickly and 14B models only with short contexts. No FP8 or BF16 support, which matters for some image and training tools.
Among the 2 devices we track with about 11 GB of usable memory, the RTX 2080 Ti 11GB is the fastest at generating text, because generation speed follows memory bandwidth. Others in the same class: Apple M4 16GB. They all hold the same models; the faster ones simply answer sooner.
Our picks for the RTX 2080 Ti 11GB
The model we would run first for each job, chosen from our recommendations by what fits fully with an 8K context. "Best quant" is the highest quality that fits; "max context" is at Q4_K_M or the native format.
| Task | Model | Best quant | Max context | Speed |
|---|---|---|---|---|
| Best all-rounder | Qwen 3.5 9B | Q8_0 | 134K | ~70 tok/s |
| Coding | Qwen 3.5 9B | Q8_0 | 134K | ~70 tok/s |
| Fastest replies | Qwen 3.5 4B | FP16 / BF16 | 221K | ~140 tok/s |
| Long documents (64K+) | Qwen 3.5 9B | Q8_0 | 134K | ~70 tok/s |
| Images in, text out | Ministral 3 14B | Q4_K_M | 12K | ~44 tok/s |
| Image generation | FLUX.1 [dev] | GGUF Q6_K | – | – |
| Spec | Value |
|---|---|
| Memory | 11 GB |
| Memory bandwidth | 616 GB/s |
| Architecture | Turing |
| Released | 2018-09 |
| Llama 3.1 8B Q4_K_M speed | ~72 tok/s |
| Largest model that fits | Qwen 3 14B |
Image and video models on the RTX 2080 Ti 11GB
Peak VRAM with model swapping (ComfyUI default on smaller cards).
| Model | FP8 | FP8 fit | GGUF Q4 | Q4 fit |
|---|---|---|---|---|
| Stable Diffusion 1.5 | 1.8 GB | Fits | 1.7 GB | Fits |
| SDXL 1.0 | 4.1 GB | Fits | 4.1 GB | Fits |
| Stable Diffusion 3.5 Medium | 6.4 GB | Fits | 6.4 GB | Fits |
| Stable Diffusion 3.5 Large | 8.6 GB | Fits | 6.4 GB | Fits |
| FLUX.1 [dev] | 12.1 GB | 86% on GPU | 7.3 GB | Fits |
| FLUX.1 [schnell] | 12.1 GB | 86% on GPU | 7.3 GB | Fits |
| Qwen-Image | 20.4 GB | 51% on GPU | 12.3 GB | 84% on GPU |
| Wan 2.2 A14B (T2V / I2V) | 18.8 GB | 55% on GPU | 13.2 GB | 78% on GPU |
| Wan 2.2 TI2V 5B | 8.0 GB | Fits | 6.5 GB | Fits |
| HunyuanVideo | 18.3 GB | 56% on GPU | 13.1 GB | 79% on GPU |
| FLUX.1 Kontext [dev] | 12.3 GB | 84% on GPU | 7.5 GB | Fits |
| FLUX.2 [dev] | 31.0 GB | 33% on GPU | 23.6 GB | 44% on GPU |
| Z-Image Turbo | 6.8 GB | Fits | 4.9 GB | Fits |
| Qwen-Image-Edit 2509 | 20.5 GB | 50% on GPU | 12.4 GB | 84% on GPU |
| LTX-2 | 19.2 GB | 54% on GPU | 12.6 GB | 82% on GPU |
Upgrade path
The next step up is the RTX 2060 12GB with 12 GB.
RTX 2080 Ti 11GB for LLMs: common questions
Can the RTX 2080 Ti 11GB run Llama 3.3 70B?
No. It needs about 43.2 GB at Q4_K_M, far more than the 11.0 GB available.
Can the RTX 2080 Ti 11GB run Qwen 3 32B?
Only partly. It needs about 21.4 GB at Q4_K_M, so about 48% fits in VRAM and the rest runs from system RAM, which is slow.
Can the RTX 2080 Ti 11GB run Qwen 3 14B?
Yes. Qwen 3 14B needs about 10.5 GB at Q4_K_M with 8K context, and the best quality that fits is IQ4_XS.
How fast is the RTX 2080 Ti 11GB for LLMs?
About 72 tokens per second for an 8B model at Q4_K_M, based on its 616 GB/s memory bandwidth. Larger models scale down roughly in proportion to their size.