NVIDIA GeForce GTX 1080 Ti
11 GB decides what fits. 484.4 GB/s decides how fast it runs once it does.
Open in the calculator →Best models for 11 GB, on every card that size →
Find one: Amazon ↗ · eBay (new and used) ↗Store links may pay us a commission. They never decide which card is suggested — the memory arithmetic does.
- 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 →
At 8,192 tokens of context with the whole model in device memory. Speeds are estimates from memory bandwidth, not benchmarks run on this card.
142 of 320 fit entirely
142 of the 320 models the engine can size fit entirely in device memory at Q4_K_M where it is published, otherwise the nearest published format, and 8,192 tokens. 75 run with some layers on system memory (32 GB assumed), and 103 do not run at all.
Featured models · Q4_K_M at 8,192 tokens, including offload
| Model | Needs | Verdict | Decode | Calculator |
|---|---|---|---|---|
| Qwen3.5-2B2.3B parameters | 2.32 GB | fits | ~267 tok/s | Open → |
| NVIDIA-Nemotron-3-Nano-4B-BF164.0B parameters | 3.46 GB | fits | ~124 tok/s | Open → |
| Qwen3-VL-8B-Instruct8.8B parameters | 7.04 GB | fits | ~56 tok/s | Open → |
| Qwen3.5-9B9.7B parameters | 7.05 GB | fits | ~68 tok/s | Open → |
| gemma-4-12B-it12B parameters | 9.54 GB | fits | ~40 tok/s | Open → |
| gpt-oss-20b21B parameters | 13.8 GB | 6 of 24 layers on system RAM (3.19 GB) | ~65 tok/s with offload | Open → |
| Qwen3.8-27B28B parameters | 18.6 GB | 29 of 64 layers on system RAM (7.73 GB) | ~7.6 tok/s with offload | Open → |
| Qwen3.6-27B28B parameters | 18.6 GB | 29 of 64 layers on system RAM (7.73 GB) | ~7.6 tok/s with offload | Open → |
| Kimi-Linear-48B-A3B-Instruct49B parameters | 30.4 GB | 18 of 27 layers on system RAM (19.6 GB) | ~46 tok/s with offload | Open → |
| Qwen3.8-Flash-Next180B parameters | 111.6 GB | needs 101.3 GB of system RAM; 32 GB assumed | does not run | Open → |
| DeepSeek-V4-Flash-Vision-Exp305B parameters | 188.1 GB | needs 178.5 GB of system RAM; 32 GB assumed | does not run | Open → |
| GLM-5.3-Flash321B parameters | 198.3 GB | needs 188.5 GB of system RAM; 32 GB assumed | does not run | Open → |
These examples are selected from prominent labs using the catalogue’s latest Hugging Face 30-day downloads and repository-creation freshness signal, with newer releases guaranteed a place. Offloaded rows assume 32 GB of system RAM, and a speed is only shown for a row that runs. Fitting in memory is not the same as loading: whether the runtime and version you have supports each architecture and format on this machine has not been tested here. Each “Open” link carries the same model, format, context and RAM into the calculator.
Fits entirely in NVIDIA GeForce GTX 1080 Ti memory — 142 of 320 sized models
The most demanding model that fits is LLaDA2.0-mini at Q4_K_M: 11.0 GB of the 11 GB, leaving 1.9 MB spare.
Fully resident at 8,192 tokens (or the model’s own maximum, where that is shorter), offload off, at 484.4 GB/s. Each row is a run of the engine for this configuration; the rows start with current, prominent releases and “fits” is memory, not a tested runtime. Older or less prominent models remain available through this search and “Show all”.
Showing 40 of 142 models that fit.
| Model | Format | Needs | Spare | Decode | Downloads / 30d | Calculator |
|---|---|---|---|---|---|---|
| Qwen3.5-9BQwen · 9.7B params | Q4_K_M | 7.05 GB | 3.95 GB | ~68 tok/s | 9M | Open → |
| Qwen3.5-4BQwen · 4.7B params | Q4_K_M | 3.98 GB | 7.02 GB | ~122 tok/s | 7.8M | Open → |
| gemma-4-12B-itGoogle · 12B params | Q4_K_M | 9.54 GB | 1.46 GB | ~40 tok/s | 1.9M | Open → |
| Qwen3.5-2BQwen · 2.3B params | Q4_K_M | 2.32 GB | 8.68 GB | ~267 tok/s | 4.9M | Open → |
| gemma-4-E4B-itGoogle · 8.0B params | Q4_K_M | 5.86 GB | 5.14 GB | ~109 tok/s | 4.4M | Open → |
| NVIDIA-Nemotron-3-Nano-4B-BF16NVIDIA · 4.0B params | Q4_K_M | 3.46 GB | 7.54 GB | ~124 tok/s | 3.4M | Open → |
| gemma-4-E2B-itGoogle · 5.1B params | Q4_K_M | 4.02 GB | 6.98 GB | ~288 tok/s | 3M | Open → |
| Qwen3.5-0.8BQwen · 873M params | Q4_K_M | 1.46 GB | 9.54 GB | ~585 tok/s | 2.6M | Open → |
| Qwen3-VL-8B-InstructQwen · 8.8B params | Q4_K_M | 7.04 GB | 3.96 GB | ~56 tok/s | 14.6M | Open → |
| North-Micro-Vision-InstructCohereLabs · 2.5B params | Q4_K_M | 2.99 GB | 8.01 GB | ~176 tok/s | 180.7K | Open → |
| granite-4.2-8bIBM · 8.8B params | Q4_K_M | 7.49 GB | 3.51 GB | ~51 tok/s | 128.4K | Open → |
| granite-4.1-3bIBM · 3.4B params | Q4_K_M | 3.72 GB | 7.28 GB | ~119 tok/s | 521.8K | Open → |
| LFM2.5-2.6BLiquidAI · 2.7B params | Q4_K_M | 2.61 GB | 8.39 GB | ~191 tok/s | 108.1K | Open → |
| Qwen3-VL-4B-InstructQwen · 4.4B params | Q4_K_M | 4.72 GB | 6.28 GB | ~89 tok/s | 3.5M | Open → |
| Qwen3-VL-2B-InstructQwen · 2.1B params | Q4_K_M | 3.05 GB | 7.95 GB | ~161 tok/s | 2.8M | Open → |
| granite-4.2-3bIBM · 3.7B params | Q4_K_M | 3.72 GB | 7.28 GB | ~119 tok/s | 50.6K | Open → |
| LFM2.5-230MLiquidAI · 230M params | Q4_K_M | 1.05 GB | 9.95 GB | ~1329 tok/s | 88.6K | Open → |
| Qwen3-0.6BQwen · 752M params | Q4_K_M | 2.22 GB | 8.78 GB | ~247 tok/s | 29.7M | Open → |
| granite-4.1-8bIBM · 8.8B params | Q4_K_M | 7.49 GB | 3.51 GB | ~51 tok/s | 179.3K | Open → |
| LFM2.5-VL-3BLiquidAI · 3.1B params | Q4_K_M | 2.85 GB | 8.15 GB | ~191 tok/s | 26.7K | Open → |
| MiMo-V2.6-Distill-Qwen-9BNEWXiaomiMiMo · 9.4B params | Q4_K_M | 6.90 GB | 4.10 GB | ~68 tok/s | 14.6K | Open → |
| Qwen3-4B-Instruct-2507Qwen · 4.0B params | Q4_K_M | 4.72 GB | 6.28 GB | ~89 tok/s | 3.7M | Open → |
| Ling-3.0-tinyinclusionAI · 7.9B params | Q4_K_M | 5.85 GB | 5.15 GB | ~384 tok/s | 17.7K | Open → |
| Qwen3-8BQwen · 8.2B params | Q4_K_M | 7.04 GB | 3.96 GB | ~56 tok/s | 10.7M | Open → |
| Olmo-3-7B-Instructallenai · 7.3B params | Q4_K_M | 7.96 GB | 3.04 GB | ~48 tok/s | 481.7K | Open → |
| Qwen3-4BQwen · 4.0B params | Q4_K_M | 4.51 GB | 6.49 GB | ~89 tok/s | 7.8M | Open → |
| LFM2.5-8B-A1BLiquidAI · 8.5B params | Q4_K_M | 6.06 GB | 4.94 GB | ~297 tok/s | 32.4K | Open → |
| LFM2.5-350MLiquidAI · 354M params | Q4_K_M | 1.13 GB | 9.87 GB | ~858 tok/s | 69.9K | Open → |
| Hy-MT2-1.8BTencent · 2.0B params | Q4_K_M | 2.47 GB | 8.53 GB | ~198 tok/s | 28.9K | Open → |
| LLaDA2.0-miniinclusionAI · 16B params | Q4_K_M | 11.0 GB | 1.9 MB | ~308 tok/s | 217.2K | Open → |
| LFM2.5-1.2B-InstructLiquidAI · 1.2B params | Q4_K_M | 1.63 GB | 9.37 GB | ~317 tok/s | 119.2K | Open → |
| Ministral-3-14B-Instruct-2512Mistral AI · 14B params | Q4_K_M | 10.4 GB | 0.62 GB | ~36 tok/s | 251K | Open → |
| Qwen3-1.7BQwen · 2.0B params | Q4_K_M | 3.02 GB | 7.98 GB | ~161 tok/s | 3.1M | Open → |
| Nemotron-3.5-Content-SafetyNVIDIA · 4.3B params | Q4_K_M | 3.73 GB | 7.27 GB | ~119 tok/s | 14.1K | Open → |
| Hy-MT2-7BTencent · 8.0B params | Q4_K_M | 6.50 GB | 4.50 GB | ~58 tok/s | 15.4K | Open → |
| GLM-4.6V-Flashzai-org · 10B params | Q4_K_M | 7.45 GB | 3.55 GB | ~57 tok/s | 103.7K | Open → |
| Qwen2.5-VL-7B-InstructQwen · 8.3B params | Q4_K_M | 6.36 GB | 4.64 GB | ~68 tok/s | 5.8M | Open → |
| SmolLM3-3BHuggingFaceTB · 3.1B params | Q4_K_M | 3.46 GB | 7.54 GB | ~131 tok/s | 617K | Open → |
| Ministral-3-8B-Instruct-2512Mistral AI · 8.9B params | Q4_K_M | 7.14 GB | 3.86 GB | ~55 tok/s | 121.2K | Open → |
| Ministral-3-3B-Instruct-2512Mistral AI · 3.8B params | Q4_K_M | 3.82 GB | 7.18 GB | ~109 tok/s | 114.1K | Open → |
Sized at the format most people actually download, not at FP16. The catalogue ordered by downloads →
Find the NVIDIA GeForce GTX 1080 Ti: Amazon ↗ · eBay (new and used) ↗Store links may pay us a commission. They never decide which card is suggested — the memory arithmetic does.
The specification behind every figure
What the manufacturer publishes for this device, and the pages it was read from.
Manufacturer specification
| Memory scope | dedicated |
|---|---|
| Capacity | 11 GB |
| Published options | 11 GB |
| Bandwidth | 484.4 GB/s |
| Memory type | GDDR5X |
| Bus width | 352-bit |
| FP32 peak | Not published |
| Dense matrix peak | Not published without sparsity |
| TDP (third-party) | 250 W |
Source ledger
Caveats
- NVIDIA no longer publishes a specification page for the GTX 10 series, so every figure here comes from the TechPowerUp GPU Database (https://www.techpowerup.com/gpu-specs/geforce-gtx-1080-ti.c2877), a third-party source, and is labelled as an estimate rather than a published specification.
- GTX 10 cards have no tensor cores and older CUDA support; llama.cpp still runs on them, some newer runtimes do not.
- No dense matrix throughput is published for this device in a form this catalogue accepts, so no compute roof is priced and time to first token is withheld.
Published capacity is a hardware ceiling, not guaranteed free runtime memory. The calculator shows the runtime reserve separately rather than folding it into a single number.
Run the diagnostic on the NVIDIA GeForce GTX 1080 Ti →