Best local LLMs for 11 GB VRAM
Every catalogued model that fits entirely in 11 GB, with no layers moved to system RAM. Speeds are estimated on the NVIDIA GeForce GTX 1080 Ti, the most common 11 GB card in Steam's hardware survey.
- Largest popular model that fitsLLaDA2.0-mini16B params · Q4_K_M · needs 11.0 GB~308 tok/s Faster than you readOpen in the calculator →
- Most downloaded that fitsQwen3.5-9B9.7B params · Q4_K_M · needs 7.05 GB~68 tok/s Faster than you readOpen in the calculator →
“Best” is not a quality ranking. The picks are the largest widely downloaded model that fits, the largest that still answers at 30 tokens a second or more, and the most downloaded; the list puts current, widely downloaded releases first. Speeds are estimates from memory bandwidth, not benchmarks.
Is 11 GB of VRAM enough for a local LLM?
For models under 9B parameters, yes: all 124 in the catalogue fit entirely at Q4_K_M, the format most people download. In the 9B to 16B band, 16 of 21 fit. All 142 that fit answer at 30 tokens a second or more on the NVIDIA GeForce GTX 1080 Ti, which is faster than most people read. A longer conversation needs more memory than the 8,192 tokens counted here, and a smaller format than Q4_K_M needs less; the calculator sizes either.
| Model size | Fit in 11 GB | For example |
|---|---|---|
| Under 4B parameters | 66 of 66 | Qwen3.5-2B · needs 2.32 GB |
| 4B to 9B parameters | 58 of 58 | Qwen3.5-4B · needs 3.98 GB |
| 9B to 16B parameters | 16 of 21 | Qwen3.5-9B · needs 7.05 GB |
| 16B to 36B parameters | 1 of 66 | LLaDA2.0-mini · needs 11.0 GB |
| 36B and larger parameters | 0 of 51 | none fits entirely |
Models that fit in 11 GB
| Model | Parameters | Needs | Spare | Decode | Answer |
|---|---|---|---|---|---|
| Qwen3.5-9B Qwen · Q4_K_M | 9.7B | 7.05 GB | 3.95 GB | ~68 tok/s | Details |
| Qwen3.5-4B Qwen · Q4_K_M | 4.7B | 3.98 GB | 7.02 GB | ~122 tok/s | Details |
| gemma-4-12B-it Google · Q4_K_M | 12B | 9.54 GB | 1.46 GB | ~40 tok/s | Details |
| Qwen3.5-2B Qwen · Q4_K_M | 2.3B | 2.32 GB | 8.68 GB | ~267 tok/s | Details |
| gemma-4-E4B-it Google · Q4_K_M | 8.0B | 5.86 GB | 5.14 GB | ~109 tok/s | Details |
| NVIDIA-Nemotron-3-Nano-4B-BF16 NVIDIA · Q4_K_M | 4.0B | 3.46 GB | 7.54 GB | ~124 tok/s | Details |
| gemma-4-E2B-it Google · Q4_K_M | 5.1B | 4.02 GB | 6.98 GB | ~288 tok/s | Details |
| Qwen3.5-0.8B Qwen · Q4_K_M | 873M | 1.46 GB | 9.54 GB | ~585 tok/s | Details |
| Qwen3-VL-8B-Instruct Qwen · Q4_K_M | 8.8B | 7.04 GB | 3.96 GB | ~56 tok/s | Details |
| North-Micro-Vision-Instruct CohereLabs · Q4_K_M | 2.5B | 2.99 GB | 8.01 GB | ~176 tok/s | Details |
| granite-4.2-8b IBM · Q4_K_M | 8.8B | 7.49 GB | 3.51 GB | ~51 tok/s | Details |
| granite-4.1-3b IBM · Q4_K_M | 3.4B | 3.72 GB | 7.28 GB | ~119 tok/s | Details |
| LFM2.5-2.6B LiquidAI · Q4_K_M | 2.7B | 2.61 GB | 8.39 GB | ~191 tok/s | Details |
| Qwen3-VL-4B-Instruct Qwen · Q4_K_M | 4.4B | 4.72 GB | 6.28 GB | ~89 tok/s | Details |
| Qwen3-VL-2B-Instruct Qwen · Q4_K_M | 2.1B | 3.05 GB | 7.95 GB | ~161 tok/s | Details |
| granite-4.2-3b IBM · Q4_K_M | 3.7B | 3.72 GB | 7.28 GB | ~119 tok/s | Details |
| LFM2.5-230M LiquidAI · Q4_K_M | 230M | 1.05 GB | 9.95 GB | ~1329 tok/s | Details |
| Qwen3-0.6B Qwen · Q4_K_M | 752M | 2.22 GB | 8.78 GB | ~247 tok/s | Details |
| granite-4.1-8b IBM · Q4_K_M | 8.8B | 7.49 GB | 3.51 GB | ~51 tok/s | Details |
| LFM2.5-VL-3B LiquidAI · Q4_K_M | 3.1B | 2.85 GB | 8.15 GB | ~191 tok/s | Details |
| MiMo-V2.6-Distill-Qwen-9B XiaomiMiMo · Q4_K_M | 9.4B | 6.90 GB | 4.10 GB | ~68 tok/s | Details |
| Qwen3-4B-Instruct-2507 Qwen · Q4_K_M | 4.0B | 4.72 GB | 6.28 GB | ~89 tok/s | Details |
| Ling-3.0-tiny inclusionAI · Q4_K_M | 7.9B | 5.85 GB | 5.15 GB | ~384 tok/s | Details |
| Qwen3-8B Qwen · Q4_K_M | 8.2B | 7.04 GB | 3.96 GB | ~56 tok/s | Details |
| Olmo-3-7B-Instruct allenai · Q4_K_M | 7.3B | 7.96 GB | 3.04 GB | ~48 tok/s | Details |
| Qwen3-4B Qwen · Q4_K_M | 4.0B | 4.51 GB | 6.49 GB | ~89 tok/s | Details |
| LFM2.5-8B-A1B LiquidAI · Q4_K_M | 8.5B | 6.06 GB | 4.94 GB | ~297 tok/s | Details |
| LFM2.5-350M LiquidAI · Q4_K_M | 354M | 1.13 GB | 9.87 GB | ~858 tok/s | Details |
| Hy-MT2-1.8B Tencent · Q4_K_M | 2.0B | 2.47 GB | 8.53 GB | ~198 tok/s | Details |
| LLaDA2.0-mini inclusionAI · Q4_K_M | 16B | 11.0 GB | 1.9 MB | ~308 tok/s | Details |
| LFM2.5-1.2B-Instruct LiquidAI · Q4_K_M | 1.2B | 1.63 GB | 9.37 GB | ~317 tok/s | Details |
| Ministral-3-14B-Instruct-2512 Mistral AI · Q4_K_M | 14B | 10.4 GB | 0.62 GB | ~36 tok/s | Details |
| Qwen3-1.7B Qwen · Q4_K_M | 2.0B | 3.02 GB | 7.98 GB | ~161 tok/s | Details |
| Nemotron-3.5-Content-Safety NVIDIA · Q4_K_M | 4.3B | 3.73 GB | 7.27 GB | ~119 tok/s | Details |
| Hy-MT2-7B Tencent · Q4_K_M | 8.0B | 6.50 GB | 4.50 GB | ~58 tok/s | Details |
| GLM-4.6V-Flash zai-org · Q4_K_M | 10B | 7.45 GB | 3.55 GB | ~57 tok/s | Details |
| Qwen2.5-VL-7B-Instruct Qwen · Q4_K_M | 8.3B | 6.36 GB | 4.64 GB | ~68 tok/s | Details |
| SmolLM3-3B HuggingFaceTB · Q4_K_M | 3.1B | 3.46 GB | 7.54 GB | ~131 tok/s | Details |
| Ministral-3-8B-Instruct-2512 Mistral AI · Q4_K_M | 8.9B | 7.14 GB | 3.86 GB | ~55 tok/s | Details |
| Ministral-3-3B-Instruct-2512 Mistral AI · Q4_K_M | 3.8B | 3.82 GB | 7.18 GB | ~109 tok/s | Details |
2 devices with 11 GB
The same models fit on every one of them. What changes is speed, which follows memory bandwidth: a card with twice the bandwidth decodes roughly twice as fast.
| Device | Bandwidth | Memory | Where to find one |
|---|---|---|---|
| NVIDIA GeForce GTX 1080 Ti speeds on this page | 484.4 GB/s | 11 GB, dedicated | Amazon ↗ · eBay (new and used) ↗ |
| NVIDIA GeForce RTX 2080 Ti | 616 GB/s | 11 GB, dedicated | Amazon ↗ · eBay (new and used) ↗ |
Which card to buy, at every memory size →
Store links may pay us a commission. They never decide which models are listed — the memory arithmetic does.
What does not fit in 11 GB
Widely downloaded models that need more than 11 GB at Q4_K_M, and the smallest memory size that holds each one entirely. Each link shows what 11 GB can still do with it: a smaller format, or part of the model in system RAM at a lower speed.
| Model | Needs | Fits from | On 11 GB |
|---|---|---|---|
| Qwen3-14B | 11.1 GB | 12 GB | On 11 GB |
| Qwen2.5-Coder-14B-Instruct | 11.4 GB | 12 GB | On 11 GB |
| gpt-oss-20b | 13.8 GB | 16 GB | On 11 GB |
| gpt-oss-safeguard-20b | 13.8 GB | 16 GB | On 11 GB |
| Qwen3.8-27B | 18.6 GB | 20 GB | On 11 GB |
| gemma-4-26B-A4B-it | 16.8 GB | 20 GB | On 11 GB |
5 more models fit in 12 GB. Best local LLMs for 12 GB →